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" and examples explicitly instruct the agent to "search for relevant information," "find credible sources," and add citations from external/public sources (e.g., Stack Overflow, McKinsey, Gartner) — clearly ingesting untrusted third-party web content for interpretation.