git-commit-pr
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and prioritize repository-specific conventions and instructions from local files, which creates a surface for indirect prompt injection if those files contain malicious content.
- Ingestion points: The skill explicitly instructs the agent to read
AGENTS.md,CLAUDE.md,.github/instructions/*,.github/prompts/*, and existing merged PR bodies to determine workflow rules. - Boundary markers: Absent. There are no specific delimiters or instructions to ignore embedded natural language commands found within the ingested repository files.
- Capability inventory: The skill has the ability to perform file system writes (
git commit), network operations (git push), and remote repository management (gh pr create/edit). - Sanitization: Absent. The skill encourages the agent to derive commit scopes and PR descriptions directly from the repository's context and history without sanitizing the input.
Audit Metadata