commit-archaeology-red-flags
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository data (commit messages) which could contain malicious instructions. Ingestion points: Git log commands in SKILL.md. Boundary markers: Shell commands use specific delimiters like %x01 and %x02 to separate fields. Capability inventory: Restricted to git metadata reads, awk, and grep. Sanitization: The use of structured log formats isolates commit data from command structures.
Audit Metadata