git-commit-helper
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted data from the repository source code.
- Ingestion points: The skill executes git diff commands in SKILL.md to analyze staged changes.
- Boundary markers: The skill includes explicit instructions in SKILL.md to 'STOP' and present generated messages for user approval.
- Capability inventory: The skill uses git diff for analysis in SKILL.md and produces natural language output for commit messages.
- Sanitization: No automated sanitization is performed; the skill relies on user review.
- [COMMAND_EXECUTION]: The skill uses local Git commands like 'git diff --cached' in SKILL.md to perform its primary function. These are standard, non-destructive read operations.
Audit Metadata