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.md's "Conduct Research" instructions explicitly require the agent to "search for relevant information," "find credible sources," and "extract key facts" (e.g., citing public sources like Stack Overflow and McKinsey), which means the agent will ingest open/public, potentially user-generated content that can materially influence its writing and actions.