content-research-writer

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Conduct Research" instructions explicitly tell the agent to "search for relevant information," "find credible sources," and "extract key facts, quotes, and data" (with examples citing public sources like Stack Overflow, McKinsey, Gartner), which requires fetching and interpreting open/public third‑party content that could be untrusted.