postmortem
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill ingests untrusted data from conversations and local files to generate reports. Ingestion points: Conversation history and INCIDENT.md. Boundary markers: None; the skill does not use delimiters to isolate the source text from its instructions. Capability inventory: File system write access to create or update markdown files. Sanitization: None; the skill relies on the LLM to interpret raw conversation data directly.
Audit Metadata