session-wrap-up
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes session history, including conversation logs and tool outputs, which are external data sources that could contain malicious instructions designed to influence the retrospective report.
- Ingestion points: The skill processes conversation history, tool outputs, and working-tree status as described in SKILL.md.
- Boundary markers: No explicit delimiters are used to isolate the ingested session data, which may lead the agent to follow instructions found within the logs during analysis.
- Capability inventory: The skill is primarily a reporting tool restricted to read-only checks and does not perform file modifications or network requests without user approval.
- Sanitization: The instructions do not specify any sanitization or filtering of the session content being reviewed.
Audit Metadata