renovate-migrate

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses GitHub PR comments using gh pr view <pr-number> --json comments to extract a "Dependency Upgrade Review" and then uses that user-generated review content to drive code migrations, which exposes the agent to untrusted third-party input that can influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes an external runtime fetch via the GitHub CLI (gh pr view --json comments --jq '...') to read a PR review comment and then uses the review's "Required Code Changes" content to directly guide code migrations, so external PR comment content can control agent behavior.