code-review

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

• Third-party content exposure detected (low risk: 0.10). The skill reviews local code diffs and changes, and optionally fetches upstream guidelines from a specific trusted GitHub URL upon user request, neither of which involves monitoring or consuming outsider-authored free text queues.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch instructions and commits from GitHub (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and the GitHub API) at runtime to refresh its interface guidelines.