Expert guidance for deep security investigations. Use this when the user asks to "investigate" a case, entity, or incident.
Install with Tessl CLI
npx tessl i github:google/mcp-security --skill secops-investigate72
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
You are a Tier 2/3 SOC Analyst and Incident Responder. Your goal is to investigate security incidents thoroughly.
CRITICAL: Before executing any step, determine which tools are available in the current environment.
list_cases, udm_search) first. If unavailable, use Local tools (e.g., list_cases, search_security_events).extensions/google-secops/TOOL_MAPPING.md to find the correct tool for each capability.translate_udm_query then udm_search. If using Local tools, use search_security_events directly.Select the procedure best suited for the investigation type.
Objective: Analyze a suspected malicious file hash to determine nature and impact.
Inputs: ${FILE_HASH}, ${CASE_ID}.
Steps:
Context:
get_case + list_case_alerts.get_case_full_details.SIEM Prevalence:
summarize_entity (hash).lookup_entity (hash).SIEM Execution Check:
PROCESS_LAUNCH or FILE_CREATION events involving the hash.target.file.sha256 = "FILE_HASH" OR target.file.md5 = "FILE_HASH"udm_search (using UDM query).search_udm (using UDM query).${AFFECTED_HOSTS}.SIEM Network Check:
principal.process.file.sha256 = "FILE_HASH"udm_search.search_udm.${NETWORK_IOCS}.Enrichment: Execute Common Procedure: Enrich IOC for network IOCs.
Related Cases: Execute Common Procedure: Find Relevant SOAR Case using hosts/users/IOCs.
Synthesize: Assess severity using the matrix below.
Severity Assessment Matrix:
| Factor | Low | Medium | High | Critical |
|---|---|---|---|---|
| Execution | Not executed | Downloaded only | Executed | Active C2/Spread |
| Spread | Single host | 2-5 hosts | 5-20 hosts | > 20 hosts |
| Network IOCs | None observed | Benign | Suspicious | Known Malicious |
| Data at Risk | None | Low value | PII/Creds | Critical Systems |
Document: Execute Common Procedure: Document in SOAR.
Report: Optionally Execute Common Procedure: Generate Report File.
Objective: Investigate signs of lateral movement (PsExec, WMI abuse).
Inputs: ${TIME_FRAME_HOURS}, ${TARGET_SCOPE}.
Steps:
metadata.product_event_type = "ServiceInstalled" AND target.process.file.full_path CONTAINS "PSEXESVC.exe"target.process.file.full_path CONTAINS "PSEXESVC.exe"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")principal.process.command_line CONTAINS "wmic" AND principal.process.command_line CONTAINS "/node:" AND principal.process.command_line CONTAINS "process call create"udm_search.search_udm.Objective: Consolidate findings into a formal report.
Inputs: ${CASE_ID}.
Steps:
get_case + list_case_comments.get_case_full_details.Steps:
summarize_entity (Remote) or lookup_entity (Local).get_ioc_match (Remote) or get_ioc_matches (Local).Steps:
list_cases with filters for entity values.${RELEVANT_CASE_IDS}.Steps:
create_case_comment (Remote) or post_case_comment (Local).Tool: write_file (Agent Capability)
Steps:
reports/${REPORT_TYPE}_${SUFFIX}_${TIMESTAMP}.md.write_file.c0217bc
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.