git-commit-format
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions purely as a set of instructions for the AI agent to format user-provided text into structured Git commit messages. It contains no executable scripts, shell commands, or network-bound operations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user descriptions of code changes (ingestion point in SKILL.md description). While there are no explicit boundary markers or sanitization steps defined in the instructions, the skill has no associated capabilities (no command execution, file system access, or network tools) that could be exploited by malicious data, resulting in a safe ingestion surface.
Audit Metadata