synthesis-fact-checking

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md) explicitly requires searching and verifying claims on open/public sites — e.g., "Use Google Scholar, the publisher's website, or the institution's publications page," "search for the paper by title," and "search for the exact quote...using quotation marks" — so the agent is expected to ingest and act on untrusted third-party web content that can influence verification and publishing decisions.