open-pr

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several shell commands to manage the git workflow and repository metadata.
  • Executes git commands (e.g., git rev-parse, git rev-list, git log, git commit --amend, git show, git diff) to inspect the branch state and history.
  • Executes gh (GitHub CLI) commands to fetch repository information and create pull requests.
  • Executes a local Python script located at .github/scripts/pr_hygiene.py to validate branch names, commit messages, and PR content.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository environment which could influence agent behavior.
  • Ingestion points: Reads branch names via git rev-parse, commit messages via git log, and file contents/diffs via git show and git diff. It also reads the PR template from the repository.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings when processing commit messages or the PR body content.
  • Capability inventory: The skill has the capability to execute shell commands (python3, git, gh), write to the /tmp/ directory, and perform network operations via gh pr create.
  • Sanitization: There is no explicit sanitization mentioned for the content extracted from commit logs or branch names before they are passed as arguments to the hygiene script or included in the final PR submission.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 07:58 AM