conventional-commits
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No instructions found that attempt to override AI safety guidelines or agent behavior.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network requests are present in the skill.
- [Remote Code Execution] (SAFE): There are no patterns for downloading or executing remote code or packages.
- [Indirect Prompt Injection] (LOW): The skill processes user-provided commit descriptions to format them. However, since the skill has no executable capabilities (no file system, network, or shell access), the risk of malicious instructions being executed through data is negligible.
Audit Metadata