pr-comment-resolver

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs fetching PR review comments via GitHub CLI/API (see "PR Comment Commands" like gh pr view ... --comments and gh api repos/{owner}/{repo}/pulls/{pr_number}/comments) and the Workflow ("Read
• Get comment content and context") requires the agent to read and act on those user-generated review comments, which are untrusted third-party content that can materially influence actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill issues GitHub CLI/API calls at runtime (e.g., "gh api repos/{owner}/{repo}/pulls/{pr_number}/comments" and "gh api repos/{owner}/{repo}/pulls/{pr_number}/reviews") to fetch reviewer comments that directly drive the agent's actions/instructions, so the fetched external content can control prompts.