verify-claims

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly fetches and reads public web pages as part of its workflow—e.g., "Fetch: https://en.wikipedia.org/wiki/List_of_fact-checking_websites" and using web_fetch to retrieve fact‑checker articles found via DuckDuckGo site: searches—thereby ingesting third‑party web content that could carry indirect prompt‑injection.