catchup
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data originating from Git commit messages and file contents (via grep for TODO/FIXME markers).
- Ingestion points: External data enters the agent context through
git logandgrepoperations inSKILL.md. - Boundary markers: The skill does not explicitly instruct the agent to ignore or delimit instructions found within the commit messages or file comments.
- Capability inventory: The skill performs read-only operations using
git,grep,jq, and basic shell utilities. It does not perform network operations or write to the file system. - Sanitization: There is no sanitization of the strings retrieved from Git logs or files before they are presented to the agent.
Audit Metadata