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 example outputs explicitly say it will "search for relevant information," "find credible sources," and add citations (e.g., citing McKinsey, Stack Overflow and other public sites), which implies fetching and reading untrusted public web content and user-generated sources as part of its workflow.