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 scripts/fact_checker.py (verify_claim_with_grounding) calls Gemini's Google Search grounding (types.GoogleSearch) to fetch web search results and include the resulting "search_context" and grounding URLs from public websites in the verification prompt, so untrusted third‑party web content is ingested and directly influences the agent's judgments.