pr-writer
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
gitandgh(GitHub CLI) to automate pull request management tasks such as viewing branch status, inspecting diffs, and creating or updating pull requests.\n - Evidence:
SKILL.mdinvokes commands likegit branch,git status,gh pr view,gh pr create, andgh api.\n- [EXTERNAL_DOWNLOADS]: The evaluation workflow uses a utility from a well-known service (Netlify) to run quality checks.\n - Evidence:
EVAL.mdreferences the use ofnpx @netlify/axis.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git diffs and existing pull request descriptions, which is an inherent attack surface for indirect prompt injection, though the impact is limited to influencing the generated PR text.\n - Ingestion points: The skill reads branch diffs via
git diffand PR metadata viagh pr view.\n - Boundary markers: No explicit markers are used to isolate untrusted content from the instructions.\n
- Capability inventory: The skill has the ability to create and update pull requests via the GitHub CLI.\n
- Sanitization: No explicit content sanitization is mentioned in the provided instructions.
Audit Metadata