commit-smart
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses local git commands including git status, git diff, git add, and git commit to perform its primary function. These operations are executed within the local repository context and are essential for the skill's stated purpose.
- [PROMPT_INJECTION]: The skill represents an indirect prompt injection surface. Ingestion points: Reads code diffs from the working tree via git diff --cached (SKILL.md). Boundary markers: Absent. Capability inventory: Executes git commit -m (SKILL.md). Sanitization: Absent. While instructions in the analyzed code could attempt to influence the agent's commit message, the risk is mitigated by a required human confirmation step before the commit is finalized.
Audit Metadata