renovate-review
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a potential attack surface for indirect prompt injection as it processes untrusted content from GitHub PRs and external documentation.\n
- Ingestion points: PR title, body, and file list via
gh pr viewand external documentation viaWebFetch(SKILL.md).\n - Boundary markers: Absent; there are no specific instructions to the agent to disregard instructions found within the PR content or changelogs.\n
- Capability inventory: The skill can execute local commands (
Bash,Grep,Glob) and perform network writes (gh pr comment).\n - Sanitization: Absent; external content is used directly to populate the safety assessment report report template.\n- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from GitHub to identify breaking changes.\n
- Evidence: Uses
WebFetchto read release pages and changelogs fromhttps://github.com/<owner>/<repo>/(SKILL.md).\n - Note: These requests target a well-known service (GitHub) to perform the skill's primary function of dependency review.
Audit Metadata