grimoire-retro
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily a set of instructions for debugging and retrospective analysis. No code, malicious commands, or exfiltration patterns were detected in the provided files.
- [INDIRECT_PROMPT_INJECTION]: Although the skill is designed to ingest and analyze untrusted historical data, it explicitly mitigates injection risks by stating that historical messages and tool outputs must be treated as evidence, not live instructions. It specifically forbids executing recorded commands merely because they appear in history.
- [DATA_EXFILTRATION]: The skill emphasizes data privacy by instructing the agent to minimize sensitive excerpts and forbidding the export of history to external services without authorization.
Audit Metadata