file-pr
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, specifically repository pull request templates and existing pull request descriptions.
- Ingestion points: The skill attempts to read pull request templates (e.g.,
.github/pull_request_template.md) and fetches existing PR content usinggh pr view <pr> --json title,bodyinSKILL.md. - Boundary markers: The instructions do not define clear delimiters or include safety warnings to ignore embedded instructions within the fetched template or PR body content.
- Capability inventory: The skill possesses capabilities to write files, push changes to remote repositories (
git push), and create/edit resources on GitHub (gh pr create,gh pr edit). - Sanitization: The skill lacks explicit sanitization or validation steps for content read from external templates or existing PRs before interpolating it into the final PR body.
Audit Metadata