retro
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill addresses potential data exposure by instructing the agent to read only specific session logs and to ensure no secrets or personal data are included in the output.
- [INDIRECT_PROMPT_INJECTION]: The skill processes session logs, which are external data sources. The instructions mitigate injection risks by focusing the agent on generating improvement suggestions for the user rather than performing automated system actions.
- [SAFE]: The skill configuration includes
disable-model-invocation: true, which limits the model's autonomy and serves as a security constraint.
Audit Metadata