commit-guidelines
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read repository documentation, commit logs, and diffs to determine commit scope and style. This creates a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: SKILL.md (Step 1 under 'Read the repository first').
- Boundary markers: None provided for content read from the repository.
- Capability inventory: The skill authorizes git operations and running repository-defined tests, linters, and build tools.
- Sanitization: There are no instructions for sanitizing content read from the repository.
Audit Metadata