investigate-history
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill incorporates strong security principles, specifically limiting actions to read-only traversal and prohibiting any modification of the worktree, configuration, or remote server state.
- [PROMPT_INJECTION]: The instructions proactively mitigate indirect prompt injection risks by explicitly warning the agent to treat repository files, commit messages, and issue text as data rather than authoritative instructions.
- [DATA_EXFILTRATION]: While the skill allows for bounded object transfer (e.g., git fetch), it restricts this to history completeness and prohibits broad data exposure or hidden network access.
Audit Metadata