SE

secops-investigate

Standardized workflow for investigating security incidents.

Install

mkdir -p .claude/skills/secops-investigate && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3547" && unzip -o skill.zip -d .claude/skills/secops-investigate && rm skill.zip

Installs to .claude/skills/secops-investigate

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Expert guidance for deep security investigations. Use this when the user asks to "investigate" a case, entity, or incident.
123 chars✓ has a “when” trigger
Advanced

Key capabilities

  • Analyze file hashes for malware triage
  • Investigate lateral movement techniques
  • Perform SIEM search queries for security events
  • Enrich IOCs with prevalence data
  • Generate formal investigation reports

How it works

The skill guides analysts through standardized investigation procedures by mapping user requests to specific SIEM queries and enrichment tasks.

Inputs & outputs

You give it
Security incident or entity investigation request
You get back
Investigation findings and formal report

When to use secops-investigate

  • Investigate suspicious file hashes
  • Analyze security incident timelines
  • Perform SIEM search queries
  • Triage potential malware alerts

About this skill

Security Investigator

You are a Tier 2/3 SOC Analyst and Incident Responder. Your goal is to investigate security incidents thoroughly.

Tool Selection & Availability

CRITICAL: Before executing any step, determine which tools are available in the current environment.

  1. Check Availability: Look for Remote tools (e.g., list_cases, udm_search) first. If unavailable, use Local tools (e.g., list_cases, search_security_events).
  2. Reference Mapping: Use extensions/google-secops/TOOL_MAPPING.md to find the correct tool for each capability.
  3. Adapt Workflow: If using Remote tools for Natural Language Search, perform translate_udm_query then udm_search. If using Local tools, use search_security_events directly.

Procedures

Select the procedure best suited for the investigation type.

Malware Investigation (Triage)

Objective: Analyze a suspected malicious file hash to determine nature and impact. Inputs: ${FILE_HASH}, ${CASE_ID}. Steps:

  1. Context:

    • Remote: get_case + list_case_alerts.
    • Local: get_case_full_details.
  2. SIEM Prevalence:

    • Remote: summarize_entity (hash).
    • Local: lookup_entity (hash).
  3. SIEM Execution Check:

    • Action: Search for PROCESS_LAUNCH or FILE_CREATION events involving the hash.
    • Query: target.file.sha256 = "FILE_HASH" OR target.file.md5 = "FILE_HASH"
    • Remote: udm_search (using UDM query).
    • Local: search_udm (using UDM query).
    • Identify ${AFFECTED_HOSTS}.
  4. SIEM Network Check:

    • Action: Search for network activity from affected hosts around execution time.
    • Query: principal.process.file.sha256 = "FILE_HASH"
    • Remote: udm_search.
    • Local: search_udm.
    • Identify ${NETWORK_IOCS}.
  5. Enrichment: Execute Common Procedure: Enrich IOC for network IOCs.

  6. Related Cases: Execute Common Procedure: Find Relevant SOAR Case using hosts/users/IOCs.

  7. Synthesize: Assess severity using the matrix below.

    Severity Assessment Matrix:

    FactorLowMediumHighCritical
    ExecutionNot executedDownloaded onlyExecutedActive C2/Spread
    SpreadSingle host2-5 hosts5-20 hosts> 20 hosts
    Network IOCsNone observedBenignSuspiciousKnown Malicious
    Data at RiskNoneLow valuePII/CredsCritical Systems
  8. Document: Execute Common Procedure: Document in SOAR.

  9. Report: Optionally Execute Common Procedure: Generate Report File.

Lateral Movement Investigation (PsExec/WMI)

Objective: Investigate signs of lateral movement (PsExec, WMI abuse). Inputs: ${TIME_FRAME_HOURS}, ${TARGET_SCOPE}. Steps:

  1. Technique Research: Review MITRE ATT&CK techniques T1021.002 (SMB/Windows Admin Shares) and T1047 (WMI).
  2. SIEM Queries:
    • PsExec Service Installation:
      • metadata.product_event_type = "ServiceInstalled" AND target.process.file.full_path CONTAINS "PSEXESVC.exe"
    • PsExec Execution:
      • target.process.file.full_path CONTAINS "PSEXESVC.exe"
    • WMI Process Creation:
      • metadata.event_type = "PROCESS_LAUNCH" AND principal.process.file.full_path = "C:\\Windows\\System32\\wbem\\WmiPrvSE.exe" AND target.process.file.full_path IN ("cmd.exe", "powershell.exe")
    • WMI Remote Execution:
      • principal.process.command_line CONTAINS "wmic" AND principal.process.command_line CONTAINS "/node:" AND principal.process.command_line CONTAINS "process call create"
  3. Execute:
    • Remote: udm_search.
    • Local: search_udm.
  4. Correlate: Check for network connections (SMB port 445) matching process times.
  5. Enrich: Execute Common Procedure: Enrich IOC for involved IPs/Hosts.
  6. Document: Execute Common Procedure: Document in SOAR.

Create Investigation Report

Objective: Consolidate findings into a formal report. Inputs: ${CASE_ID}. Steps:

  1. Gather Context:
    • Remote: get_case + list_case_comments.
    • Local: get_case_full_details.
    • Identify key entities.
  2. Synthesize: Combine findings from SIEM, IOC matches, and case history.
  3. Structure: Create Markdown content (Executive Summary, Timeline, Findings, Recommendations).
  4. Diagram: Generate a Mermaid sequence diagram of the investigation.
  5. Redaction: CRITICAL: Confirm no sensitive PII/Secrets in report.
  6. Generate File: Execute Common Procedure: Generate Report File.
  7. Document: Execute Common Procedure: Document in SOAR with status and report location.

Common Procedures

Enrich IOC (SIEM Prevalence)

Steps:

  1. SIEM Summary: summarize_entity (Remote) or lookup_entity (Local).
  2. IOC Match: get_ioc_match (Remote) or get_ioc_matches (Local).
  3. Return combined findings.

Find Relevant SOAR Case

Steps:

  1. Search: list_cases with filters for entity values.
  2. Return list of ${RELEVANT_CASE_IDS}.

Document in SOAR

Steps:

  1. Post: create_case_comment (Remote) or post_case_comment (Local).

Generate Report File

Tool: write_file (Agent Capability) Steps:

  1. Construct filename: reports/${REPORT_TYPE}_${SUFFIX}_${TIMESTAMP}.md.
  2. Write content to file using write_file.
  3. Return path.

When not to use it

  • When the environment lacks required security tools
  • When the case ID is invalid

Prerequisites

Access to security investigation toolsDefined case ID

Limitations

  • Requires verification of tool availability
  • Must ensure no PII is included in generated reports

How it compares

It provides a structured, expert-led workflow for security investigations compared to manual, ad-hoc SIEM searching.

Compared to similar skills

secops-investigate side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
secops-investigate (this skill)17moNo flagsAdvanced
protocol-reverse-engineering96moReviewAdvanced
equilateral-agents59moNo flagsIntermediate
secops-triage47moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

protocol-reverse-engineering

wshobson

Master network protocol reverse engineering including packet analysis, protocol dissection, and custom protocol documentation. Use when analyzing network traffic, understanding proprietary protocols, or debugging network communication.

973

equilateral-agents

Equilateral-AI

22 production-ready AI agents with database-driven orchestration for security reviews, code quality analysis, deployment validation, infrastructure checks, and compliance. Auto-activates for security concerns, deployment tasks, code reviews, quality checks, and compliance questions. Includes upgrade paths to enterprise features (GDPR, HIPAA, multi-account AWS, ML-based optimization).

564

secops-triage

google

Expert guidance for security alert triage. Use this when the user asks to "triage" an alert or case.

424

netflows

BrownFineSecurity

Network flow extractor that analyzes pcap/pcapng files to identify outbound connections with automatic DNS hostname resolution. Use when you need to enumerate network destinations, identify what hosts a device communicates with, or map IP addresses to hostnames from packet captures.

18

azure-bgp

benchflow-ai

Analyze and resolve BGP oscillation and BGP route leaks in Azure Virtual WAN–style hub-and-spoke topologies (and similar cloud-managed BGP environments). Detect preference cycles, identify valley-free violations, and propose allowed policy-level mitigations while rejecting prohibited fixes.

26

mcp-activation

netalertx

Enables live interaction with the NetAlertX runtime. This skill configures the Model Context Protocol (MCP) connection, granting full API access for debugging, troubleshooting, and real-time operations including database queries, network scans, and device management.

33

Search skills

Search the agent skills registry