macos-linux-worktree-repo-operations

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill instructs the agent to fetch and read user-generated GitHub content (e.g., via gh pr view, gh api repos/{owner}/{repo}/pulls//comments and GraphQL reviewThreads) — untrusted third-party PR/issue comments and review bodies that the agent is expected to interpret as part of its workflow.