research-claim-map

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (Step 2: "Gather and categorize evidence" in SKILL.md and the Triangulation/Cross-Checking sections in resources/methodology.md) explicitly directs the agent to consult and interpret open public sources—e.g., Snopes/FactCheck/PolitiFact, Google Scholar/PubMed/Web of Science, SEC EDGAR, social media, and web archives—which are untrusted/user-generated third‑party content that could influence decisions and thus enable indirect prompt injection.