content-research-writer

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

• Third-party content exposure detected (high risk: 1.00). The skill's "Conduct Research" workflow explicitly instructs the agent to "search for relevant information," "find credible sources," and "extract key facts, quotes, and data" (see the "Conduct Research" section and examples referencing public sources like Stack Overflow, Gartner, McKinsey), which indicates it will fetch and ingest open/public third-party content that the agent reads and uses to influence writing and decisions.