content-research-writer

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

• Third-party content exposure detected (high risk: 0.80). This skill's "Conduct Research" section in SKILL.md explicitly instructs the agent to "search for relevant information", "find credible sources", and "extract key facts, quotes, and data" from external sources, which requires fetching and reading open/public third‑party content (websites, reports, transcripts) that could include untrusted/user‑generated material.