gemini-review-integrator

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches Gemini Code Assist PR review comments via ${CLAUDE_PLUGIN_ROOT}/scripts/fetch-gemini-comments.sh (Step 2) and parses the comments' body and suggestion code blocks to decide what to integrate and how to update the PR review comment (Steps 5–6), so untrusted/user-generated third‑party content can directly influence agent behavior.