fact-checker

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 2 Verifier explicitly uses Google Search (see call_gemini(..., use_search=True) and VERIFY_PROMPT in scripts/fact_checker.py and ARCHITECTURE.md) to fetch and interpret open web search results for each claim, so untrusted third‑party content can directly influence verification decisions and follow‑up actions.