review-pr-in-worktree

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of local shell commands to manage the development environment.
  • Executes git fetch, git worktree add, and git worktree remove to manage the lifecycle of a PR review worktree.
  • Uses the gh (GitHub CLI) tool to retrieve pull request metadata, status, and merge information from GitHub.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted text data from external Pull Requests, which could contain malicious instructions.
  • Ingestion points: The skill retrieves the PR body, reviews, and comments using the gh pr view command in Step 2 and Step 6. This content is then provided to the agent for analysis.
  • Boundary markers: The skill body does not specify any explicit delimiters or 'ignore embedded instructions' warnings for the data retrieved from the PR.
  • Capability inventory: The skill possesses capabilities for filesystem modification (git worktree operations), network access to GitHub (git fetch), and it invokes a secondary skill (/review-a-pr-and-report) which is described as running the repository's test gate (code execution).
  • Sanitization: There is no mention of sanitization, escaping, or filtering of the external PR content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 01:25 AM