postmortem-generator

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes incident data from external sources including PagerDuty, JIRA, and ServiceNow. This untrusted data is interpolated into the final postmortem document, creating a surface for indirect prompt injection.
  • Ingestion points: Incident management MCP tools and timeline.csv.
  • Boundary markers: None present.
  • Capability inventory: File system writes, execution of gh CLI for bug filing, and document generation via Workspace extension.
  • Sanitization: None detected.
  • [EXTERNAL_DOWNLOADS]: Mentions a Workspace extension from the author's GitHub repository (github.com/gemini-cli-extensions/workspace) to generate Google Docs.
  • [COMMAND_EXECUTION]: Utilizes the gh CLI to automate the filing of issues on GitHub based on identified action items.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 01:11 AM
Security Audit — agent-trust-hub — postmortem-generator