commit-message
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes untrusted code changes and git diffs which could contain malicious instructions designed to manipulate the generated commit message. 1. Ingestion points: File contents and git diffs processed by analyze_changes.py. 2. Boundary markers: No delimiters or ignore instructions are used to isolate untrusted code. 3. Capability inventory: Restricted to text generation for commit messages. 4. Sanitization: No sanitization of the input code content is mentioned.
- Command Execution (SAFE): The skill declares the use of a local Python script .shared/commit-message/scripts/analyze_changes.py for its core logic, which is standard behavior for an AI agent skill.
Audit Metadata