content-research-writer

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Conduct Research" workflow explicitly instructs the agent to "search for relevant information", "find credible sources", and "extract key facts, quotes, and data" from external references (e.g., cited public sources like McKinsey and Stack Overflow) — i.e., it ingests and acts on untrusted public web content as part of its core workflow.