postmortem-review
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from users regarding software bugs and root cause analyses. This content is used to populate postmortem documents and a global memory file, creating a surface for persisting malicious instructions.
- Ingestion points: User input provided during Step 1 (Collecting Information) and Step 3 (Creating Postmortem Documentation) in
SKILL.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the generated documents.
- Capability inventory: The skill performs file-write operations to the local project directory (
docs/postmortem/) and to a global memory path (~/.agents/memory/lessons-learned.md). - Sanitization: There is no evidence of sanitization or validation of the input before it is written to the memory files.
Audit Metadata