postmortem
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely composed of Markdown-based instructions and templates for document generation with no executable code.
- [SAFE]: No network operations, data exfiltration patterns, or external downloads are performed or initiated by this skill.
- [SAFE]: The skill does not access sensitive local files, environment variables, or include any hardcoded credentials.
- [SAFE]: The instructions are focused on the structure and quality of the report and do not contain patterns for prompt injection or safety guideline bypasses.
- [SAFE]: While the skill processes an 'incident' argument which constitutes an indirect prompt injection surface, it lacks high-privilege capabilities such as shell access or network requests that would make this surface exploitable. Ingestion points: 'incident' argument; Boundary markers: Absent; Capability inventory: None (text generation only); Sanitization: Absent.
Audit Metadata