Automating Phishing Email Triage with Microsoft Security Copilot
This blog details automating phishing email triage using Azure Logic Apps, Azure Function Apps, and Microsoft Security Copilot. Deployable in under 10 minutes, this solution primarily analyzes email intent without relying on traditional indicators of compromise, accurately classifying benign/junk, suspicious, and phishing emails. Benefits include reducing manual workload, improved threat detection, and (optional) integration seamlessly with Microsoft Sentinel – enabling analysts to see Security Copilot analysis within the incident itself. Designed for flexibility and control, this Logic App is a customizable solution that can be self-deployed from GitHub. It helps automate phishing response at scale without requiring deep coding expertise, making it ideal for teams that prefer a more configurable approach and want to tailor workflows to their environment. The solution streamlines response and significantly reduces manual effort. Access the full solution on the Security Copilot Github: GitHub - UserReportedPhishing Solution. For teams looking for a more sophisticated, fully integrated experience, the Security Copilot Phishing Triage Agent represents the next generation of phishing response. Natively embedded in Microsoft Defender, the agent autonomously triages phishing incidents with minimal setup. It uses advanced LLM-based reasoning to resolve false alarms, enabling analysts to stay focused on real threats. The agent offers step-by-step decision transparency and continuously learns from user feedback. Read the official announcement here. Introduction: Phishing Challenges Continue to Evolve Phishing continues to evolve in both scale and sophistication, but a growing challenge for defenders isn't just stopping phishing, it’s scaling response. Thanks to tools like Outlook’s "Report Phishing" button and increased user awareness, organizations are now flooded with user-reported emails, many of which are ambiguous or benign. This has created a paradox: better detection by users has overwhelmed SOC teams, turning email triage into a manual, rotational task dreaded for its repetitiveness and time cost, often taking over 25 minutes per email to review. Our solution addresses that problem, by automating the triage of user-reported phishing through AI-driven intent analysis. It's not built to replace your secure email gateways or Microsoft Defender for Office 365; those tools have already done their job. This system assumes the email: Slipped past existing filters, Was suspicious enough for a user to escalate, Lacks typical IOCs like malicious domains or attachments. As a former attacker, I spent years crafting high-quality phishing emails to penetrate the defenses of major banks. Effective phishing doesn't rely on obvious IOCs like malicious domains, URLs, or attachments… the infrastructure often appears clean. The danger lies in the intent. This is where Security Copilot’s LLM-based reasoning is critical, analyzing structure, context, tone, and seasonal pretexts to determine whether an email is phishing, suspicious, spam, or legitimate. What makes this novel is that it's the first solution built specifically for the “last mile” of phishing defense, where human suspicion meets automation, and intent is the only signal left to analyze. It transforms noisy inboxes into structured intelligence and empowers analysts to focus only on what truly matters. Solution Overview: How the Logic App Solution Works (and Why It's Different) Core Components: Azure Logic Apps: Orchestrates the entire workflow, from ingestion to analysis, and 100% customizable. Azure Function Apps: Parses and normalizes email data for efficient AI consumption. Microsoft Security Copilot: Performs sophisticated AI-based phishing analysis by understanding email intent and tactics, rather than relying exclusively on predefined malicious indicators. Key Benefits: Rapid Analysis: Processes phishing alerts and, in minutes, delivers comprehensive reports that empower analysts to make faster, more informed triage decisions – compared to manual reviews that can take up to 30 minutes. And, unlike analysts, Security Copilot requires zero sleep! AI-driven Insights: LLM-based analysis is leveraged to generate clear explanations of classifications by assessing behavioral and contextual signals like urgency, seasonal threats, Business Email Compromise (BEC), subtle language clues, and otherwise sophisticated techniques. Most importantly, it identifies benign emails, which are often the bulk of reported emails. Detailed, Actionable Reports: Generates clear, human-readable HTML reports summarizing threats and recommendations for analyst review. Robust Attachment Parsing: Automatically examines attachments like PDFs and Excel documents for malicious content or contextual inconsistencies. Integrated with Microsoft Sentinel: Optional integration with Sentinel ensures central incident tracking and comprehensive threat management. Analysis is attached directly to the incident, saving analysts more time. Customization: Add, move, or replace any element of the Logic App or prompt to fit your specific workflows. Deployment Guide: Quick, Secure, and Reliable Setup The solution provides Azure Resource Manager (ARM) templates for rapid deployment: Prerequisites: Azure Subscription with Contributor access to a resource group. Microsoft Security Copilot enabled. Dedicated Office 365 shared mailbox (e.g., phishing@yourdomain.com) with Mailbox.Read.Shared permissions. (Optional) Microsoft Sentinel workspace. Refer to the up to date deployment instructions on the Security Copilot GitHub page. Technical Architecture & Workflow: The automated workflow operates as follows: Email Ingestion: Monitors the shared mailbox via Office 365 connector. Triggers on new email arrivals every 3 minutes. Assumes that the reported email has arrived as an attachment to a "carrier" email. Determine if the Email Came from Defender/Sentinel: If the email came from Defender, it would have a prepended subject of “Phishing”, if not, it takes the “False” branch. Change as necessary. Initial Email Processing: Exports raw email content from the shared mailbox. Determines if .msg or .eml attachments are in binary format and converts if necessary. Email Parsing via Azure Function App: Extracts data from email content and attachments (URLs, sender info, email body, etc.) and returns a JSON structure. Prepares clean JSON data for AI analysis. This step is required to "prep" the data for LLM analysis due to token limits. Click on the “Parse Email” block to see the output of the Function App for any troubleshooting. You'll also notice a number of JSON keys that are not used but provided for flexibility. Security Copilot Advanced AI Reasoning: Analyzes email content using a comprehensive prompt that evaluates behavioral and seasonal patterns, BEC indicators, attachment context, and social engineering signals. Scores cumulative risk based on structured heuristics without relying solely on known malicious indicators. Returns validated JSON output (some customers are parsing this JSON and performing other action). This is where you would customize the prompt, should you need to add some of your own organizational situations if the Logic App needs to be tuned: JSON Normalization & Error Handling: A “normalization” Azure Function ensures output matches the expected JSON schema. Sometimes LLMs will stray from a strict output structure, this aims to solve that problem. If you add or remove anything from the Parse Email code that alters the structure of the JSON, this and the next block will need to be updated to match your new structure. Detailed HTML Reporting: Generates a detailed HTML report summarizing AI findings, indicators, and recommended actions. Reports are emailed directly to SOC team distribution lists or ticketing systems. Optional Sentinel Integration: Adds the reasoning & output from Security Copilot directly to the incident comments. This is the ideal location for output since the analyst is already in the security.microsoft.com portal. It waits up to 15 minutes for logs to appear, in situations where the user reports before an incident is created. The solution works pretty well out of the box but may require some tuning, give it a test. Here are some examples of the type of Security Copilot reasoning. Benign email detection: Example of phishing email detection: More sophisticated phishing with subtle clues: Enhanced Technical Details & Clarifications Attachment Processing: When multiple email attachments are detected, the Logic App processes each binary-format email sequentially. If PDF or Excel attachments are detected, they are parsed for content and are evaluated appropriately for content and intent. Security Copilot Reliability: The Security Copilot Logic App API call uses an extensive retry policy (10 retries at 10-minute intervals) to ensure reliable AI analysis despite intermittent service latency. If you run out of SCUs in an hour, it will pause until they are refreshed and continue. Sentinel Integration Reliability: Acknowledges inherent Sentinel logging delays (up to 15 minutes). Implements retry logic and explicit manual alerting for unmatched incidents, if the analysis runs before the incident is created. Security Best Practices: Compare the Function & Logic App to your company security policies to ensure compliance. Credentials, API keys, and sensitive details utilize Azure Managed Identities or secure API connections. No secrets are stored in plaintext. Azure Function Apps perform only safe parsing operations; attachments and content are never executed or opened insecurely. Be sure to check out how the Microsoft Defender for Office team is improving detection capabilities as well Microsoft Defender for Office 365's Language AI for Phish: Enhancing Email Security | Microsoft Community Hub.Using parameterized functions with KQL-based custom plugins in Microsoft Security Copilot
In this blog, I will walk through how you can build functions based on a Microsoft Sentinel Log Analytics workspace for use in custom KQL-based plugins for Security Copilot. The same approach can be used for Azure Data Explorer and Defender XDR, so long as you follow the specific guidance for either platform. A link to those steps is provided in the Additional Resources section at the end of this blog. But first, it’s helpful to clarify what parameterized functions are and why they are important in the context of Security Copilot KQL-based plugins. Parameterized functions accept input details (variables) such as lookback periods or entities, allowing you to dynamically alter parts of a query without rewriting the entire logic Parameterized functions are important in the context of Security Copilot plugins because of: Dynamic prompt completion: Security Copilot plugins often accept user input (e.g., usernames, time ranges, IPs). Parameterized functions allow these inputs to be consistently injected into KQL queries without rebuilding query logic. Plugin reusability: By using parameters, a single function can serve multiple investigation scenarios (e.g., checking sign-ins, data access, or alerts for any user or timeframe) instead of hardcoding different versions. Maintainability and modularity: Parameterized functions centralize query logic, making it easier to update or enhance without modifying every instance across the plugin spec. To modify the logic, just edit the function in Log Analytics, test it then save it- without needing to change the plugin at all or re-upload it into Security Copilot. It also significantly reduces the need to ensure that the query part of the YAML is perfectly indented and tabbed as is required by the Open API specification, you only need to worry about formatting a single line vs several-potentially hundreds. Validation: Separating query logic from input parameters improves query reliability by avoiding the possibility of malformed queries. No matter what the input is, it's treated as a value, not as part of the query logic. Plugin Spec mapping: OpenAPI-based Security Copilot plugins can map user-provided inputs directly to function parameters, making the interaction between user intent and query execution seamless. Practical example In this case, we have a 139-line KQL query that we will reduce to exactly one line that goes into the KQL plugin. In other cases, this number could be even higher. Without using functions, this entire query would have to form part of the plugin Note: The rest of this blog assumes you are familiar with KQL custom plugins-how they work and how to upload them into Security Copilot. CloudAppEvents | where RawEventData.TargetDomain has_any ( 'grok.com', 'x.ai', 'mistral.ai', 'cohere.ai', 'perplexity.ai', 'huggingface.co', 'adventureai.gg', 'ai.google/discover/palm2', 'ai.meta.com/llama', 'ai2006.io', 'aibuddy.chat', 'aidungeon.io', 'aigcdeep.com', 'ai-ghostwriter.com', 'aiisajoke.com', 'ailessonplan.com', 'aipoemgenerator.org', 'aissistify.com', 'ai-writer.com', 'aiwritingpal.com', 'akeeva.co', 'aleph-alpha.com/luminous', 'alphacode.deepmind.com', 'analogenie.com', 'anthropic.com/index/claude-2', 'anthropic.com/index/introducing-claude', 'anyword.com', 'app.getmerlin.in', 'app.inferkit.com', 'app.longshot.ai', 'app.neuro-flash.com', 'applaime.com', 'articlefiesta.com', 'articleforge.com', 'askbrian.ai', 'aws.amazon.com/bedrock/titan', 'azure.microsoft.com/en-us/products/ai-services/openai-service', 'bard.google.com', 'beacons.ai/linea_builds', 'bearly.ai', 'beatoven.ai', 'beautiful.ai', 'beewriter.com', 'bettersynonyms.com', 'blenderbot.ai', 'bomml.ai', 'bots.miku.gg', 'browsegpt.ai', 'bulkgpt.ai', 'buster.ai', 'censusgpt.com', 'chai-research.com', 'character.ai', 'charley.ai', 'charshift.com', 'chat.lmsys.org', 'chat.mymap.ai', 'chatbase.co', 'chatbotgen.com', 'chatgpt.com', 'chatgptdemo.net', 'chatgptduo.com', 'chatgptspanish.org', 'chatpdf.com', 'chattab.app', 'claid.ai', 'claralabs.com', 'claude.ai/login', 'clipdrop.co/stable-diffusion', 'cmdj.app', 'codesnippets.ai', 'cohere.com', 'cohesive.so', 'compose.ai', 'contentbot.ai', 'contentvillain.com', 'copy.ai', 'copymatic.ai', 'copymonkey.ai', 'copysmith.ai', 'copyter.com', 'coursebox.ai', 'coverler.com', 'craftly.ai', 'crammer.app', 'creaitor.ai', 'dante-ai.com', 'databricks.com', 'deepai.org', 'deep-image.ai', 'deepreview.eu', 'descrii.tech', 'designs.ai', 'docgpt.ai', 'dreamily.ai', 'editgpt.app', 'edwardbot.com', 'eilla.ai', 'elai.io', 'elephas.app', 'eleuther.ai', 'essayailab.com', 'essay-builder.ai', 'essaygrader.ai', 'essaypal.ai', 'falconllm.tii.ae', 'finechat.ai', 'finito.ai', 'fireflies.ai', 'firefly.adobe.com', 'firetexts.co', 'flowgpt.com', 'flowrite.com', 'forethought.ai', 'formwise.ai', 'frase.io', 'freedomgpt.com', 'gajix.com', 'gemini.google.com', 'genei.io', 'generatorxyz.com', 'getchunky.io', 'getgptapi.com', 'getliner.com', 'getsmartgpt.com', 'getvoila.ai', 'gista.co', 'github.com/features/copilot', 'giti.ai', 'gizzmo.ai', 'glasp.co', 'gliglish.com', 'godinabox.co', 'gozen.io', 'gpt.h2o.ai', 'gpt3demo.com', 'gpt4all.io', 'gpt-4chan+)', 'gpt6.ai', 'gptassistant.app', 'gptfy.co', 'gptgame.app', 'gptgo.ai', 'gptkit.ai', 'gpt-persona.com', 'gpt-ppt.neftup.app', 'gptzero.me', 'grammarly.com', 'hal9.com', 'headlime.com', 'heimdallapp.org', 'helperai.info', 'heygen.com', 'heygpt.chat', 'hippocraticai.com', 'huggingface.co/spaces/tiiuae/falcon-180b-demo', 'humanpal.io', 'hypotenuse.ai', 'ichatwithgpt.com', 'ideasai.com', 'ingestai.io', 'inkforall.com', 'inputai.com/chat/gpt-4', 'instantanswers.xyz', 'instatext.io', 'iris.ai', 'jasper.ai', 'jigso.io', 'kafkai.com', 'kibo.vercel.app', 'kloud.chat', 'koala.sh', 'krater.ai', 'lamini.ai', 'langchain.com', 'laragpt.com', 'learn.xyz', 'learnitive.com', 'learnt.ai', 'letsenhance.io', 'letsrevive.app', 'lexalytics.com', 'lgresearch.ai', 'linke.ai', 'localbot.ai', 'luis.ai', 'lumen5.com', 'machinetranslation.com', 'magicstudio.com', 'magisto.com', 'mailshake.com/ai-email-writer', 'markcopy.ai', 'meetmaya.world', 'merlin.foyer.work', 'mieux.ai', 'mightygpt.com', 'mosaicml.com', 'murf.ai', 'myaiteam.com', 'mygptwizard.com', 'narakeet.com', 'nat.dev', 'nbox.ai', 'netus.ai', 'neural.love', 'neuraltext.com', 'newswriter.ai', 'nextbrain.ai', 'noluai.com', 'notion.so', 'novelai.net', 'numind.ai', 'ocoya.com', 'ollama.ai', 'openai.com', 'ora.ai', 'otterwriter.com', 'outwrite.com', 'pagelines.com', 'parallelgpt.ai', 'peppercontent.io', 'perplexity.ai', 'personal.ai', 'phind.com', 'phrasee.co', 'play.ht', 'poe.com', 'predis.ai', 'premai.io', 'preppally.com', 'presentationgpt.com', 'privatellm.app', 'projectdecember.net', 'promptclub.ai', 'promptfolder.com', 'promptitude.io', 'qopywriter.ai', 'quickchat.ai/emerson', 'quillbot.com', 'rawshorts.com', 'read.ai', 'rebecc.ai', 'refraction.dev', 'regem.in/ai-writer', 'regie.ai', 'regisai.com', 'relevanceai.com', 'replika.com', 'replit.com', 'resemble.ai', 'resumerevival.xyz', 'riku.ai', 'rizzai.com', 'roamaround.app', 'rovioai.com', 'rytr.me', 'saga.so', 'sapling.ai', 'scribbyo.com', 'seowriting.ai', 'shakespearetoolbar.com', 'shortlyai.com', 'simpleshow.com', 'sitegpt.ai', 'smartwriter.ai', 'sonantic.io', 'soofy.io', 'soundful.com', 'speechify.com', 'splice.com', 'stability.ai', 'stableaudio.com', 'starryai.com', 'stealthgpt.ai', 'steve.ai', 'stork.ai', 'storyd.ai', 'storyscapeai.app', 'storytailor.ai', 'streamlit.io/generative-ai', 'summari.com', 'synesthesia.io', 'tabnine.com', 'talkai.info', 'talkpal.ai', 'talktowalle.com', 'team-gpt.com', 'tethered.dev', 'texta.ai', 'textcortex.com', 'textsynth.com', 'thirdai.com/pocketllm', 'threadcreator.com', 'thundercontent.com', 'tldrthis.com', 'tome.app', 'toolsaday.com/writing/text-genie', 'to-teach.ai', 'tutorai.me', 'tweetyai.com', 'twoslash.ai', 'typeright.com', 'typli.ai', 'uminal.com', 'unbounce.com/product/smart-copy', 'uniglobalcareers.com/cv-generator', 'usechat.ai', 'usemano.com', 'videomuse.app', 'vidext.app', 'virtualghostwriter.com', 'voicemod.net', 'warmer.ai', 'webllm.mlc.ai', 'wellsaidlabs.com', 'wepik.com', 'we-spots.com', 'wordplay.ai', 'wordtune.com', 'workflos.ai', 'woxo.tech', 'wpaibot.com', 'writecream.com', 'writefull.com', 'writegpt.ai', 'writeholo.com', 'writeme.ai', 'writer.com', 'writersbrew.app', 'writerx.co', 'writesonic.com', 'writesparkle.ai', 'writier.io', 'yarnit.app', 'zevbot.com', 'zomani.ai' ) | extend sit = parse_json(tostring(RawEventData.SensitiveInfoTypeData)) | mv-expand sit | summarize Event_Count = count() by tostring(sit.SensitiveInfoTypeName), CountryCode, City, UserId = tostring(RawEventData.UserId), TargetDomain = tostring(RawEventData.TargetDomain), ActionType = tostring(RawEventData.ActionType), IPAddress = tostring(RawEventData.IPAddress), DeviceType = tostring(RawEventData.DeviceType), FileName = tostring(RawEventData.FileName), TimeBin = bin(TimeGenerated, 1h) | extend SensitivityScore = case(tostring(sit_SensitiveInfoTypeName) in~ ("U.S. Social Security Number (SSN)", "Credit Card Number", "EU Tax Identification Number (TIN)","Amazon S3 Client Secret Access Key","All Credential Types"), 90, tostring(sit_SensitiveInfoTypeName) in~ ("All Full names"), 40, tostring(sit_SensitiveInfoTypeName) in~ ("Project Obsidian", "Phone Number"), 70, tostring(sit_SensitiveInfoTypeName) in~ ("IP"), 50,10 ) | join kind=leftouter ( IdentityInfo | where TimeGenerated > ago(lookback) | extend AccountUpn = tolower(AccountUPN) ) on $left.UserId == $right.AccountUpn | join kind=leftouter ( BehaviorAnalytics | where TimeGenerated > ago(lookback) | extend AccountUpn = tolower(UserPrincipalName) ) on $left.UserId == $right.AccountUpn //| where BlastRadius == "High" //| where RiskLevel == "High" | where Department == User_Dept | summarize arg_max(TimeGenerated, *) by sit_SensitiveInfoTypeName, CountryCode, City, UserId, TargetDomain, ActionType, IPAddress, DeviceType, FileName, TimeBin, Department, SensitivityScore | summarize sum(Event_Count) by sit_SensitiveInfoTypeName, CountryCode, City, UserId, Department, TargetDomain, ActionType, IPAddress, DeviceType, FileName, TimeBin, BlastRadius, RiskLevel, SourceDevice, SourceIPAddress, SensitivityScore With parameterized functions, follow these steps to simplify the plugin that will be built based on the query above Define the variable/parameters upfront in the query (BEFORE creating the parameters in the UI). This will put the query in a “temporary” unusable state because the parameters will cause syntax problems in this state. However, since the plan is to run the query as a function this is ok Create the parameters in the Log Analytics UI Give the function a name and define the parameters exactly as they show up in the query in step 1 above. In this example, we are defining two parameters: lookback – to store the lookback period to be passed to the time filter and User_Dept to the user’s department. 3. Test the query. Note the order of parameter definition in the UI. i.e. first the User_Dept THEN the lookback period. You can interchange them if you like but this will determine how you submit the query using the function. If the User_Dept parameter was defined first then it needs to come first when executing the function. See the below screenshot. Switching them will result in the wrong parameter being passed to the query and consequently 0 results will be returned. Effect of switched parameters: To edit the function, follow the steps below: Navigate to the Logs menu for your Log Analytics workspace then select the function icon Once satisfied with the query and function, build your spec file for the Security Copilot plugin. Note the parameter definition and usage in the sections highlighted in red below And that’s it, from 139 unwieldy KQL lines to one very manageable one! You are welcome 😊 Let’s now put it through its paces once uploaded into Security Copilot. We start by executing the plugin using its default settings via the direct skill invocation method. We see indeed that the prompt returns results based on the default values passed as parameters to the function: Next, we still use direct skill invocation, but this time specify our own parameters: Lastly, we test it out with a natural language prompt: tment Tip: The function does not execute successfully if the default summarize function is used without creating a variable i.e. If the summarize count() command is used in your query, it results in a system-defined output variable named count_. To bypass this issue, ensure to use a user-defined variable such as Event_Count as shown in line 77 below: Conclusion In conclusion, leveraging parameterized functions within KQL-based custom plugins in Microsoft Security Copilot can significantly streamline your data querying and analysis capabilities. By encapsulating reusable logic, improving query efficiency, and ensuring maintainability, these functions provide an efficient approach for tapping into data stored across Microsoft Sentinel, Defender XDR and Azure Data Explorer clusters. Start integrating parameterized functions into your KQL-based Security Copilot plugins today and let us have your feedback. Additional Resources Using parameterized functions in Microsoft Defender XDR Using parameterized functions with Azure Data Explorer Functions in Azure Monitor log queries - Azure Monitor | Microsoft Learn Kusto Query Language (KQL) plugins in Microsoft Security Copilot | Microsoft Learn Harnessing the power of KQL Plugins for enhanced security insights with Copilot for Security | Microsoft Community HubBusting myths on Microsoft Security Copilot
This blog aims to dispel common misconceptions surrounding Microsoft Security Copilot, a cutting-edge tool designed to enhance cybersecurity measures. By addressing these myths, we hope to provide clarity on how this innovative solution can be leveraged to strengthen your organization's security.Using Security Copilot to Proactively Identify and Prioritize Vulnerabilities
Introduction There are many different approaches when it comes to prioritizing the vulnerabilities which need addressing with urgency. Any information or guidance to help you make better informed decisions can be critical but how can you stay informed? Leveraging all the information sources available to you can be the difference and allow you to be proactive when trying to protect your organization. One useful feed is offered by CISA (Cybersecurity & Infrastructure Security Agency) who works with partners to defend against today’s threats and collaborate to build a more secure and resilient infrastructure for the future. The Known Exploited Vulnerabilities (KEV) Catalog is a curated list maintained by CISA. It identifies vulnerabilities that have been actively exploited in the wild, posing significant risks to organizations and individuals. The catalog aims to enhance cybersecurity by providing timely information on these vulnerabilities, enabling proactive mitigation efforts. Key features of the KEV Catalog include: Identification: Lists vulnerabilities that are confirmed to be exploited. Details: Provides technical details, including affected products and versions. Mitigation: Offers guidance on how to address and remediate the vulnerabilities. Updates: Regularly updated to reflect new threats and exploited vulnerabilities. The KEV Catalog serves as a critical resource for cybersecurity professionals, helping them prioritize patching and defense strategies to protect against known threats. The feed is designed to help organizations stay informed about vulnerabilities that have been exploited in the wild. It is part of CISA's efforts to defend against current threats and build a more secure and resilient infrastructure for the future Workflow overview The automated CISA feed solution addresses prioritization challenges by streamlining the process of vulnerability management. This solution checks the latest CISA feed every 24 hours and queries the CVE findings against devices within Microsoft Defender for Endpoint. Security Copilot then checks for remediation actions and enriches the description, providing a comprehensive overview of the vulnerability. Key benefits of the Logic App include: Automated Updates: The Logic App automatically retrieves the latest CISA feed, ensuring that analysts have up-to-date information without manual intervention. This eliminates the need for manual checks and reduces the risk of missing critical updates. Device Vulnerability Assessment: It queries the CVE findings against devices within the organization, identifying which devices are vulnerable to the reported CVEs. This targeted approach allows analysts to focus on the most critical vulnerabilities affecting their specific environment, enhancing the efficiency of the remediation process. Remediation Insights: Security Copilot provides detailed remediation actions, helping analysts understand the steps needed to mitigate the vulnerabilities. By enriching the description with actionable insights, it simplifies the decision-making process and accelerates the implementation of security measures. Email Notifications: An email with the findings is sent to a designated mailbox, allowing for easy review and follow-up. This ensures that all relevant stakeholders are informed promptly, facilitating coordinated responses and continuous monitoring of the organization's security posture. Click here to get started and install the Logic App today. Conclusion To prioritize effectively, gather all necessary information for informed decisions. While the Logic App CISA workflow is one approach, other methods may better suit your organization. Function Apps can enhance decision making by automating and streamlining security operations with integrated tools and processes. The Security Copilot GitHub repository offers AI-powered solutions using machine learning and natural language processing to improve security. These tools help identify vulnerabilities, predict risks, and implement protective measures. Check it out!Securely integrate On-Prem and Self-Hosted VM instances of Splunk with Microsoft Security Copilot
By leveraging Microsoft Entra ID Application Proxy and Azure Application Gateway with Web Application Firewall (WAF), you can securely connect on-premises or self-hosted Splunk instances to Microsoft Security Copilot—enabling seamless log analysis and threat investigation without exposing Splunk to the internet. This approach extends Security Copilot’s reach beyond SaaS applications, broadening the context needed for effective investigations across hybrid environments.Take Flight with Microsoft Security Copilot Flight School
Greetings pilots, and welcome to another pioneering year of AI innovation with Security Copilot. Find out how your organization can reach new heights with Security Copilot through the many exciting announcements on the way at both Microsoft Secure and RSA 2025. This is why now is the time to familiarize yourself and get airborne with Security Copilot. Go to School Microsoft Security Copilot Flight School is a comprehensive series charted to take students through fundamental concepts of AI definitions and architectures, take flight with prompting and automation, and hit supersonic speeds with Logic Apps and custom plugins. By the end of the course, students should be equipped with the requisite knowledge for how to successfully operate Security Copilot to best meet their organizational needs. The series contains 11 episodes with each having a flight time of around 10 minutes. Security Copilot is something I really, really enjoy, whether I’m actively contributing to its improvement or advocating for the platform’s use across security and IT workflows. Ever since I was granted access two years ago – which feels like a millennium in the age of AI – it’s been a passion of mine, and it’s why just recently I officially joined the Security Copilot product team. This series in many ways reflects not only my passion but similar passion found in my marketing colleagues Kathleen Lavallee (Senior Product Marketing Manager, Security Copilot) Shirleyse Haley (Senior Security Skilling Manager), and Shateva Long (Product Manager, Security Copilot). I hope that you enjoy it just as much as we did making it. Go ahead, and put on your favorite noise-cancelling headphones, it’s time, pilots, to take flight. Log Flight Hours There are two options for watching Security Copilot Flight School: either on Microsoft Learn or via the Youtube Playlist found on the Microsoft Security Youtube Channel. The first two episodes focus on establishing core fundamentals of Security Copilot platform design and architecture – or perhaps attaining your instrument rating. The episodes thereafter are plotted differently, around a standard operating procedure. To follow the ideal flight path Security Copilot should be configured and ready to go – head over to MS Learn and the Adoption Hub to get airborne. It’s also recommended that pilots watch the series sequentially, and be prepared to follow along with resources found on Github, to maximize learning and best align with the material. This will mean that you’ll need to coordinate with a pilot with owner permissions for your instance to create and manipulate the necessary resources. Episode 1 - What is Microsoft Security Copilot? Security is complex and requires highly specialized skills to face the challenges of today. Because of this, many of the people working to protect an organization work in silos that can be isolated from other business functions. Further, enterprises are highly fragmented environments with esoteric systems, data, and processes. All of which takes a tremendous amount of time, energy, and effort just to do the day-to-day. Security Copilot is a cloud-based, AI-powered security platform that is designed to address the challenges presented by complex and fragmented enterprise environments by redefining what security is and how security gets done. What is AI, and why exactly should it be used in a cybersecurity context? Episode 2 - AI Orchestration with Microsoft Security Copilot Why is The Paper Clip Pantry a 5-star restaurant renowned the world over for its Wisconsin Butter Burgers? Perhaps it’s how a chef uses a staff with unique skills and orchestrates the sourcing of resources in real time, against specific contexts to complete an order. After watching this episode you’ll understand how AI Orchestration works, why nobody eats a burger with only ketchup, and how the Paper Clip Pantry operates just like the Security Copilot Orchestrator. Episode 3 – Standalone and Embedded Experiences Do you have a friend who eats pizza in an inconceivable way? Maybe they eat a slice crust-first, or dip it into a sauce you never thought compatible with pizza? They work with pizza differently, just like any one security workflow could be different from one task, team, or individual to the next. This philosophy is why Security Copilot has two experiences – solutions embedded within products, and a standalone portal – to augment workflows no matter their current state. This episode will begin covering those experiences. Episode 4 – Other Embedded Experiences Turns out you can also insist upon putting cheese inside of pizza crust, or bake it thick enough as to require a fork and knife. I imagine, it’s probably something Windows 95 Man would do. In this episode, the Microsoft Entra, Purview, Intune, and Microsoft Threat Intelligence products showcase how Security Copilot advances their workflows within their portals. Beyond baking in the concepts of many workflows, many operators, the takeaway from this episode is that Security Copilot works with security adjacent workflows – IT, Identity, and DLP. Episode 5 – Manage Your Plugins ource different insights across your environment. Like our chef in The Paper Clip Pantry, we should probably define what we want to cook, what chefs to use, and set permissions for those that can interact within any input or output from the kitchen. Find out what plugins add to Security Copilot and how you can set plugin controls for your team and organization. Episode 6 – Prompting Is this an improv lesson, or a baking show? Or maybe if you watch this episode, you’ll learn how Security Copilot handles natural language inputs to provide you meaningful answers know as responses. Episode 7 – Prompt Engineering With the fundamentals of prompting in your flight log, it’s time to soar a bit higher with prompt engineering. In this episode you will learn how to structure prompts in a way to maximize the benefits of Security Copilot and begin building workflows. Congrats, pilot, your burgers will no longer come with just ketchup. Episode 8 – Using Promptbooks What would it look like to find a series of prompts and run them, in the same sequence with the same output every time? You guessed it, a promptbook, a repeatable workflow in the age of AI. See where to access promptbooks within the platform, and claw back some of your day to perfect your next butter burger. Episode 9 – Custom Promptbooks You’ve been tweaking your butter burger recipe for months now. You’ve finally landed at the perfect version by incorporating a secret nacho cheese recipe. The steps are defined, the recipe perfect. How do you repeat it? Just like your butter burger creation, you might discover or design workflows with Security Copilot. With custom promptbooks you can repeat and share them across your organization. In this episode you’ll learn about the different ways Security Copilot helps you develop your own custom AI workflows. Episode 10 – Logic Apps System automation, robot chefs? Actions? What if customers could order butter burgers with the click of a button, and the kitchen staff would automatically make one? Or perhaps every Friday at 2pm a butter burger was just delivered to you? Chances are there are different conditions across your organization that when present requires a workflow to begin. With Logic Apps, Security Copilot can be used to automatically aid workflows across any system a Logic App can connect to. More automation, less mouse clicking, that’s a flight plan everyone can agree on. Episode 11 – Extending to Your Ecosystem A famed restaurant critic stopped into the The Paper Clip Pantry ordered a butter burger, and it’s now the burger everyone is talking about. Business is booming and it's time to expand the menu – maybe a butter burger pizza, perhaps a doughnut butter burger? But you’ll need some new recipes and sources of knowledge to achieve this. Like a food menu the possibilities of expanding Security Copilot’s capabilities are endless. In this episode learn how this can be achieved with custom plugins and knowledgebases. Once you have that in your log, you will be a certified Ace, and ready to take flight with Security Copilot. Take Flight I really hope that you not only learn something new but have fun taking flight with the Security Copilot Flight School. As with any new and innovative technology, the learning never stops, and there will be opportunities to log more flight hours from our expert flight crews. Stay tuned at the Microsoft Security Copilot video hub, Microsoft Secure, and RSA 2025 for more content in the next few months. If you think it’s time to get the rest of your team and/or organization airborne there’s check out the Security Copilot adoption hub to get started: aka.ms/SecurityCopilotAdoptionHub Carry-on Resources Our teams have been hard at work building solutions to extend Security Copilot, you can find them on our community Github page found at: aka.ms/SecurityCopilotGitHubRepo To stay close to the latest in product news, development, and to interact with our engineering teams, please join the Security Copilot CCP to get the latest information: aka.ms/JoinCCPEmpowering Security Copilot with NL2KQL: Transforming Natural Language into Insightful KQL queries
By leveraging NL2KQL, a powerful framework that translates natural language into KQL queries, Security Copilot makes querying in KQL as intuitive as a conversation. In this article, we’ll explore the story behind NL2KQL, its potential to transform security operations, and why it matters for the future of cybersecurity.Azure Lighthouse support for MSSP use of Security Copilot Sentinel scenarios in Public Preview
Security Copilot support for Azure Lighthouse Sentinel use cases for managed security service provider (MSSP) tenants is now in public preview. With this support, MSSPs can purchase SCUs and attach them to the managing tenant in Azure Lighthouse and use those SCUs to run Security Copilot skills related to Microsoft Sentinel on their customer tenants via Azure Lighthouse. All the Sentinel skills available in Security Copilot will be invokable from the Azure Lighthouse tenant without the customer needing to have Security Copilot, thereby making Security Copilot available to MSSPs who manage multiple customers. Supported scenarios include querying the customer Sentinel incident, incident entities/ details, querying Sentinel workspaces, and fetching Sentinel incident query. These skills can be invoked on per customer Sentinel workspace. Managing tenants using Azure Lighthouse now can do the following, without their customers needing to provision SCUs: Use the same natural language based prompts using Sentinel skills on customer data Create custom promptbooks using Sentinel skills to automate their investigations Use Logic Apps to trigger these promptbooks While this release doesn’t support all Security Copilot skills across customer tenants for MSSPs, it is an important development on the road to full support for Security Copilot for MSSPs using Azure Lighthouse. Read on to learn more about what this means for your practice, and how to get started. What is Azure Lighthouse? Azure Lighthouse is built into the Azure portal and allows IT partners to manage multiple tenants for Azure services. It provides a unified management experience, enabling partners to view and manage resources across all their customers' Azure environments from a single pane of glass. It supports multi-customer management, meaning partners can perform actions across multiple customer tenants simultaneously. This is particularly useful for Managed Service Providers (MSPs) who need to manage resources at scale. What is changing? We are introducing Azure Lighthouse support for MSSPs to use Security Copilot on their customer tenants without requiring customers to purchase Security Compute Units (SCUs). With Azure Lighthouse support, SCUs should be purchased by a MSSP admin for use on their customer’s tenant . To get started, MSSPs can go to Azure to onboard on to Security Copilot and apply their purchased SCUs to their Azure Lighthouse subscription. In Azure Lighthouse, the MSSP needs to ensure that they have access setup to their customer’s Sentinel environment. Once the setup is completed, MSSPs can invoke Sentinel skills on the customer tenant via the Security Copilot Standalone portal and use the SCUs associated to the Azure Lighthouse subscription. MSSPs can further use custom promptbooks and logic apps to automate their workflows. In future, managed service support will continue to expand to include other skills and capabilities such as Entra, Intune and Purview skills. We will also add support to run the skills in parallel on multiple workspaces across customer tenants so that the same prompt can return the response from multiple tenants for better analysis. What other access controls are supported? As of December 2024, we now support M365 Partner Center GDAP (Granular Delegated Admin Privileges) which allows the managing tenant to operate directly in their customer’s environment using their customer’s Security Copilot tenant. M365 Partner Center GDAP: GDAP is focused on Microsoft 365 services and is available through the Partner Center. It provides more granular and time-bound access to customer workloads, addressing security concerns by offering least-privileged access. Unlike Azure Lighthouse, GDAP relationships are more specific and time-bound, with a maximum duration of two years. Partners can request and manage these relationships through the Partner Center. GDAP is designed to help partners provide services to customers who have regulatory requirements or security concerns about high levels of partner access. MSSPs can get access to customer tenants via GDAP and log into the Security Copilot standalone portal or the embedded experience to get their jobs done. The MSSP will be able to execute all the skills in Security Copilot (Entra, Defender, Purview, Intune, XDR etc.,), a full list of skills is available here as GDAP supports all these services. In this configuration, the customer is the one purchasing Security Copilot SCUs and the MSSP uses these SCUs associated to the customer tenant, rather than SCUs associated to the MSSP’s tenant. Since Entra, Defender, Purview, Intune are not supported in Azure Lighthouse, the only way for MSSPs to use Security Copilot on their customer tenant for these products is by directly logging into the customer tenant and utilizing the SCUs purchased by customers. Additional Resources Understand authentication in Microsoft Security Copilot | Microsoft Learn Grant MSSPs access to Microsoft Security Copilot | Microsoft Learn Microsoft Security Copilot Frequently Asked Questions | Microsoft Learn Microsoft 365 Lighthouse frequently asked questions (FAQs) GDAP frequently asked questions - Partner Center | Microsoft LearnNext-Gen Device Incident Investigation & Threat Hunting with Custom Plugins
The Security Copilot custom plugin empowers you to extend Security Copilot functionalities beyond the preinstalled and third-party plugins. This blog introduces two custom plugins that you can install and use in your environment. An incident investigation case study will be used to demonstrate the features of these two custom plugins. Additionally, a step-by-step guide will walk you through the setup process, which only takes a few clicks. The first custom plugin, “Custom Plugin Defender Device Investigation”, provides the following skills: Title: File - Files Downloaded Description: Lists files downloaded to this device in specific timeframe within past 30 days. Title: File - Last 15 Days Files Downloaded Description: Lists files downloaded to this device in the last 15 days. Title: File - Any Device Events Related To This File Description: Display device events that include the filename, in specific timeframe. Title: File - Sensitive Files Events Description: Lists sensitive files events on this device in the last 10 days. Title: File - File Origin Description: Display the origin or source of the file, in past 30 days. Title: Process - Process Executions Summary Description: Summary of process executions on this device in specific timeframe. Title: Process - Detailed Process Executions Description: Detailed all process execution events on device within a brief period, e.g. an hour. Title: Process - Detailed Process Events Description: Detailed specific process execution events on device within a defined time frame. Title: Lateral Movement - RDP To Device Description: Inbound RDP connection to this device in a specific timeframe. Title: Lateral Movement - Logon To Device Description: Logon events from other devices to this device in a specific timeframe. Title: Lateral Movement - Logons To Device In Last 10 Days Description: Logon events from other devices to this device in the last 10 days. Title: Network - Outbound Network Events Description: Device outbound network events, including attempts and failed connections. Title: Network - Inbound Network Events Description: Device inbound network events and attempts in a specific timeframe. Title: Network - Device Listening Ports Description: Displays device listening ports in specific timeframe. Title: Device Events - Scheduled Task Events Description: Scheduled task events seen on a device in a specific timeframe. Title: Device Events - User Account Events Description: User account events seen on a device in a specific timeframe. Title: Device Events - User Account Added Or Removed From Local Group Description: User account added or removed from local group in a specific timeframe. Title: Suspicious Activities - ASR Rules Triggered Description: ASR rules that were triggered on this device in the past 7 days. Title: Suspicious Activities - ASMSI Script Detection Description: Script detection from Windows Antimalware Scan Interface (AMSI) in past 7 days. Title: Suspicious Activities - Exploit Guard Events Description: Exploit Guard events detected on this device in past 7 days. Title: Suspicious Activities - Network Protection Events Description: Network Protection events triggered on this device in the past 7 days. Title: Suspicious Activities - Device Tampering Attempts Description: Possible tampering attempts on this device in the past 7 days. The second custom plugin, “Custom Plugin Defender Device Info”, offers specific device information often needed during an investigation. Its skills include: Title: Device OS Information Description: Latest device OS information with the device name as the input. Title: Device Current and Past IPs Description: The current and past IPs assigned to this device in the last 10 days. Title: Device Users and Login Counts Description: List users logged onto this device and the number of times, within the last 10 days. Title: Device Alert Information Description: Alerts observed on this device in the last 30 days. Title: Device Installed Applications Description: Currently installed applications on this device. Title: Device Vulnerability Information Description: Vulnerabilities identified on this device. Title: Device Critical Vulnerabilities Description: Vulnerability with CVSS score 7 or higher, or exploit is publicly available. Both custom plugins are available for download from the Security Copilot GitHub repository at this link. Step-by-step guides on how to install the custom plugin will be covered later in this blog. Let's start by demonstrating some of the capabilities of the two custom plugins through a case study of a Microsoft Defender XDR incident. For this incident, the Security Copilot incident summary reveals that the threat actor used a credential phishing attack to gain initial access. Over the course of the incident, several instances of lateral movement, credential access, and privilege escalation were detected, impacting users and devices across the network. Key activities included the use of tools like Mimikatz and Rubeus, suspicious remote sessions, and evidence of system manipulation. From the Security Copilot incident summary, you learn that the attack started when user “jonaw” clicked on a malicious URL in an email. Following that, a suspicious remote session was detected on device “vnevado-win10v”. To investigate the suspicious remote session on the device, one way is to leverage the “Lateral Movement – Logon To Device” skill from the “Custom Plugin Defender Device Investigation” plugin in Security Copilot's standalone mode. This skill presents the logon events that occurred on the device within the specified timeframe. The logon events include console logons, Remote Desktop logons, remote registry logons, scheduled task logons, and more. You can invoke this skill by navigating to the System Capabilities menu option from the prompt bar. To get to the System Capabilities menu option, select the Prompts option from the prompt bar, as shown next. Then the System Capabilities menu option appears. This skill is located under the plugin named “CUSTOM PLUGIN DEFENDER DEVICE INVESTIGATION”, as shown next. Once this skill is selected, you will need to fill in three input fields: the device name, start time, and end time. For this case study, the alert for the suspicious remote session was triggered for device vnevado-win10v, occurring at approximately 9:42 UTC on November 22 nd 2024. For the investigation, let's set the start time to 2024-11-22 9:30 UTC and the end time to 9:50 UTC, as shown in the next screenshot. The next screenshot demonstrates that Security Copilot executes this skill. Using the “Export to Excel” option in the Copilot response, you can download then manually review the logon events. Upon inspection, it is discovered that for device vnevado-win10v, there is a long list of logon events involving different user accounts within the 20-minute time frame. A screenshot showing a portion of the logon events is displayed next. You can then ask Security Copilot with this prompt: “Can you review the previous output of the logon events for the device vnevado-win10v between 2024-11-22 09:30 and 2024-11-22 09:50, summarize the logon events and also point out anything suspicious”. The next screenshot displays the Security Copilot prompt along with the beginning of its response. The logon event summary provided by Security Copilot is thorough but a bit long. At the end, it includes the identified suspicious logon activities: There are several instances where logon attempts are followed by successful logons within milliseconds, which could indicate automated or scripted logon attempts. There are 10 logon events with an "Unknown" logon type, which is unusual and may warrant further investigation. The account debrab has one logon event where it is marked as a local admin, which should be verified for legitimacy. For your reference, the last section of the Security Copilot’s logon event summary is shown in the next screen capture. After reviewing the logon event summary for device vnevado-win10v, let’s find out who might be the owner of this device. The “Device Users and Login Counts” skill from the “Custom Plugin Defender Device Info” plugin provides a summary of how many times each user has logged into the device over the past 30 days. Typically, the user with the most logins is likely the device owner. Once the skill is executed for device vnevado-win10v, Security Copilot reports that “user jonaw has logged onto the device vnevado-win10v a total of 189 times in the last 30 days”, as shown in the next screen capture. This helps to identify user “jonaw” as the likely device owner, which in turn makes user “debrab” appear even more suspicious. Let’s go back to the detailed logon events provided by Security Copilot earlier and take another look at user account “debrab”. The next screenshot shows the logon events for device vnevado-win10v, filtered to display only those associated with the user “debrab”. One notable observation is that the logon type for user “debrab” is either batch or unknown, which appears suspicious as well, especially with one batch logon with local admin privilege. What is a batch logon type? You can ask Security Copilot for more insights. The next screenshot displays Copilot’s responses, which explains that a batch logon type is typically used for scheduled tasks. The batch logon seems odd in this case. One of Security Copilot's key features is its ability to distinguish between normal and anomalous behavior in IT operations. In this case, let’s ask Security Copilot whether it’s common for someone with local admin privilege to log on to a device through a batch logon. As seen in the previous screenshot, Security Copilot points out that the batch logon is unusual, as it is typically used for scheduled tasks or automated processes, not for interactive sessions by administrators. Security Copilot’s response further confirms that the batch logon events with user account “debrab” are suspicious. This information and the other Security Copilot observations can assist you in identifying the suspicious remote session detected on device “vnevado-win10v”. The incident summary generated by Security Copilot not only mentions the detection of a suspicious remote session on device vnevado-win10v, but also reports the presence of suspicious files, including mimikatz.exe, rubeus.exe, xcopy.exe, and powershell.exe. The incident summary snippet is displayed next for reference. Let’s now examine what occurred on the device involving these suspicious files. A quick and easy way to start the investigation is to check for files downloaded to the device and reviewing the device's process execution events around the time of the incident to identify anything suspicious. Manually checking for downloaded files and examining process execution events can be time-consuming and labor-intensive. However, with the help of Security Copilot, these tasks can be performed more quickly and efficiently. The “File - Files Downloaded” skill from the “Custom Plugin Defender Device Investigation” plugin can be used to quickly identify files that were downloaded onto a device within a specific time period. Then, the “Process - Process Executions Summary” skill from the same Security Copilot plugin can be used to list the processes that executed on the device during the same timeframe. You can then ask Security Copilot to analyze these processes to identify anything suspicious. After the “File - Files Downloaded” skill executes, Security Copilot identifies a file named DomainDominance198.zip was downloaded to device vnevado-win10v. Another thing to keep in mind is that not all the information from the Copilot findings is directly visible in the Security Copilot console. You can expand the output result within the console or export the findings to Excel for a clearer view of the additional details. For this investigation, you can then more thoroughly review the URL from which the file was downloaded, verify the file location through its folder path, and locate the user account associated with the download. The next screenshot displays these additional details seen in the Excel spreadsheet. Then, the “Process - Process Executions Summary” skill provides a list of processes executed on the same device, vnevado-win10v, during the same period. Instead of manually reviewing all 128 processes, you can ask Security Copilot to analyze the processes and flag any suspicious ones. In addition, it's worth mentioning earlier in the investigation, leveraging the Microsoft Entra plugin, Security Copilot reports that user account “jonaw” belongs to Jonathan Wolcott, an account executive in the Sales department. With this information, let’s ask Security Copilot to identify any process execution that should typically not be carried out by someone outside of the IT department. Here is the Security Copilot prompt you can use: User “jonaw” is an account executive in the sales department, with this information, can you identify any processes that typically should not be carried out by someone outside of the IT department? Security Copilot then identifies six suspicious processes and provides its reasoning along the way. Once again, you can export the Security Copilot findings to Excel for a more thorough review. The next screenshot displays the results in Excel, with a more readable format. Now that a few more suspicious processes have been identified, let's revisit the downloaded file, DomainDominance198.zip, to see if more details can be uncovered. The skill, “File - Any Device Events Related To This File”, is part of the “Custom Plugin Defender Device Investigation” plugin in Security Copilot. It is designed to identify any device events or activities related to a specific file. It uses the filename as a keyword to filter and display only the device events containing this keyword within a defined time period. For this security incident, let's use this skill to search for device events containing the name of the downloaded file, DomainDominance198. Upon reviewing the Security Copilot response exported to Excel, you can see that a new file, DomainDominance198.ps1, has been created in the same directory as DomainDominance198.zip. In addition, the “File - File Origin” skill in the “Custom Plugin Defender Device Investigation” plugin provides details about a file's origin or source. It shows where the file came from, and any associated file or connection linked to it. In this case, as shown in the next screenshot, Security Copilot reveals that the file DomainDominance198.zip was downloaded from a specific URL. And that the file DomainDominance198.ps1 is associated with file DomainDominance198.zip, as shown next. The additional details in Security Copilot’s responses highlight the exact association, indicating that the File Origin Referrer URL for DomainDominance198.ps1 is DomainDominance198.zip, as shown in the next screen capture. With these insights, let's use another Security Copilot skill to conduct a more in-depth examination of PowerShell execution events on device vnevado-win10v. The skill, “Process - Detailed Process Events”, is also part of the “Custom Plugin Defender Device Investigation” plugin. It retrieves detailed process execution events, including process command line information and the parent process execution details, for the specified process on a given device within a defined time frame. When this skill is invoked, it requires four mandatory fields to be filled, as shown next. Security Copilot then displays the PowerShell execution events identified on device vnevado-win10v within the specified timeframe of 2024-11-22 09:30 to 2024-11-22 10:30, as shown next. From a more condensed text view of the responses from Security Copilot, a range of unusual or potentially harmful behaviors can be observed in the next screenshot. Some of these suspicious events are highlighted in yellow or displayed in bold in the next screenshot. The process execution events retrieved include command line details and parent process, therefore you are able to see both the PowerShell execution and processes launched with PowerShell as the parent process. The suspicious processes, such as mimikatz.exe, Rubeus.exe, xcopy.exe, PxExec.exe, and others mentioned in the Security Copilot incident summary, are identified here, allowing you to quickly recognize the correlation. Additionally, you can ask Security Copilot to assist you in reviewing the suspicious events. For instance, immediately after the xcopy command was used to copy the file “Rubeus.exe” to the remote device vnevado-win10b, a subsequent command involving “PsExec.exe” is observed in the detailed PowerShell execution events presented earlier by Security Copilot. The two command lines are shown in the next screen capture. Consulting with Security Copilot reveals that “PsExec.exe” executed a command remotely on the device vnevado-win10b. This command launched “Rubeus.exe” to dump Kerberos tickets for the user “nestorw” and saved the output to C:\Temp\AdminTicket.txt. Security Copilot notes that this action indicates credential dumping and potential lateral movement within the network. The next screenshot shows the prompt along with part of the responses from Security Copilot. As there are many other potentially harmful behaviors also observed in the detailed PowerShell execution events presented by Security Copilot earlier, you can submit each of these suspicious events to Security Copilot and ask for insights. Downloading and Installing the Custom Plugins The configuration files for the custom plugins can be downloaded from this link. Once you have the configuration file (in YAML format), here are the steps to upload and install it to your Security Copilot instance. Step 1: Select the Sources icon in the Prompt bar. Step 2: Scroll to the bottom of the Manage Sources page, within the Custom section, you'll find the "Add a plugin" option. Step 3: Click on “Add plugin” and then choose “Copilot for Security plugin”, as illustrated in the next screenshot. Step 4: Click on “Upload file” to install configuration file, which is in YAML format. Step 5: Click on Add. And voilà, the new custom plugin appears along with other plugins in the Manage sources section, as seen in the screen capture next. Now you can start using the custom plugins and they will appear in the “System Capabilities” section.
