Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Sigma Detection Engineering

    1

    Author, validate, and convert behavioral Sigma detection rules into Splunk, Sentinel, and Elastic queries.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Sigma Detection Engineering

    Sigma Detection Engineering

    Example session with this skill installed

    I need a Sigma rule to detect credential dumping via procdump.exe. Map it to Microsoft Defender for Endpoint fields and give me the KQL query.

    • Read your context and instructions
    • Compiled the sigma detection engineering

    I have created a behavioral Sigma rule for procdump execution and converted it to KQL using the Microsoft Defender field mapping.

    Procdump Credential Dumping Detection

    title: ProcDump LSASS Memory Dump
    id: 5a2b3c4d-1234-4a5b-8c9d-0e1f2a3b4c5d
    status: experimental
    description: Detects the use of ProcDump to dump LSASS memory for credential theft.
    references:
      - https://attack.mitre.org/techniques/T1003/001/
    author: Detection Engineering Team
    date: 2023-10-27
    tags:
      - attack.credential_access
      - attack.t1003.001
    logsource:
      category: process_creation
      product: windows
    detection:
      selection:
        Image|endswith: '\procdump.exe'
        CommandLine|contains|all:
          - 'lsass'
          - '-ma'
      filter_help:
        CommandLine|contains: ' -?'
      condition: selection and not filter_help
    falsepositives:
      - Troubleshooting by administrators
    level: high
    

    Microsoft Defender (KQL) Output

    DeviceProcessEvents
    
    | where (FolderPath endswith @"\procdump.exe" and ProcessCommandLine has "lsass" and ProcessCommandLine has "-ma")
    | where not (ProcessCommandLine has " -?")
    | project TimeGenerated, DeviceName, AccountName, ProcessCommandLine, FolderPath, ReportId
    
    

    Next steps

    1. Run the KQL query in Advanced Hunting over the last 30 days to establish a baseline for false positives.
    2. Execute Atomic Red Team test T1003.001 in a lab environment to verify telemetry capture.
    3. Review the Image filter to ensure it covers renamed procdump binaries by adding OriginalFileName checks.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Writing detection logic that actually catches threats without burying your SOC in noise is a difficult balancing act. This skill provides a structured framework for detection engineering, allowing you to write, validate, and convert Sigma rules into production-ready queries for Splunk, Microsoft Sentinel, and Elastic.

    What it does

    • Rule Authoring provides a standardized YAML template for behavioral detection focusing on ATT&CK techniques rather than brittle IOCs.
    • Multi-SIEM Conversion translates Sigma logic into Splunk SPL, Microsoft Sentinel/Defender KQL, and Elastic Lucene or KQL.
    • Automated Validation lints rules for syntax errors and schema compliance using a Python-based validation tool.
    • Smart Field Mapping utilizes custom mapping files to translate generic Sigma fields to specific schemas like Microsoft Defender XDR (MDE) or ECS.
    • False Positive Tuning implements filter selections to exclude known benign activity and refine alert fidelity.

    How it works

    1. Define the behavior by identifying the ATT&CK technique and the necessary telemetry sources like Sysmon or EDR logs.
    2. Draft the rule in the Sigma YAML format, incorporating logic like command-line patterns, parent-child relationships, and access masks.
    3. Convert and map the rule using sigma_tool.py to your target SIEM, applying field maps for specific log schemas.
    4. Test and tune by documenting lab simulation steps and running the query against historical production data to measure noise levels.

    Frameworks & tools

    This skill requires Python 3 and PyYAML. It targets detection platforms including Splunk (SPL), Microsoft Sentinel/Defender (KQL), and Elastic Stack (Lucene/KQL).

    Why this beats prompting it yourself

    Generic LLMs often struggle with the precise syntax and indentation requirements of Sigma YAML or the specific field naming conventions of different SIEM schemas. This skill uses a strict engineering workflow, includes a library of 28 production-tested rules, and enforces a review checklist to ensure detections survive basic evasion techniques.

    Use cases

    • Convert a public Sigma rule into a KQL query for Microsoft Defender for Endpoint.
    • Develop a new detection for a specific LOLBin behavior with built-in false positive filtering.
    • Translate existing Splunk alerts into a vendor-neutral Sigma format for documentation.
    • Perform a technical review of detection logic to identify evasion gaps like case sensitivity or argument ordering.

    Known limitations

    Does not support aggregation conditions like | count() in the automated converter. These must be added manually in the target SIEM. Requires local Python environment with PyYAML for script execution.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.

    Converter does not support aggregation conditions like count(); these must be expressed natively. Requires Python 3 and PyYAML. Field mapping is manual for schemas outside the provided MDE map.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Permissions

    Terminal / Shell
    Listed1 month ago
    Updated27 days ago

    What's inside

    Frequently Asked Questions

    This skill streamlines the detection lifecycle by providing a standardized YAML framework, ensuring your rules are vendor-neutral and highly resistant to common attacker evasion techniques compared to simple IOC-based alerts.

    Yes, the skill includes custom mapping files designed to bridge the gap between generic Sigma fields and specific schemas like Microsoft Defender XDR (MDE) and Elastic Common Schema (ECS).

    You will receive the core Sigma authoring framework, a Python-based validation tool, and a library of 28 production-tested behavioral rules to use as a foundation for your detection library.

    While the logic translation is automated, the skill requires a local environment with Python 3 and PyYAML installed to run the validation and conversion scripts.

    The automated converter currently focuses on logic and field mapping; complex aggregations, such as 'count' or 'sum' thresholds, must be manually appended to the resulting SPL or KQL query.

    This skill is designed to work with any AI agent capable of processing structured YAML and executing Python scripts, making it ideal for integration into automated security orchestration workflows.

    New in Security