write-conventional-commit
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses standard Git commands to analyze repository changes. The use of the '--no-ext-diff' flag is a security best practice that prevents the execution of potentially malicious external diff tools configured in the local environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data (Git diffs) to generate commit messages. (1) Ingestion points: Git diff output via git status and git diff commands in SKILL.md. (2) Boundary markers: Explicit instructions to return only the commit message and omit all commentary. (3) Capability inventory: The skill lacks network or file-write permissions, preventing exfiltration or persistence. (4) Sanitization: None. This is categorized as safe due to the lack of exploitable capabilities.
Audit Metadata