collaborative-outline

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly directs the agent to use integrations like "/search-content" and "literature-research" and to consult industry reports, technical blogs and Stack Overflow (public, user-generated sources) to fill the marked "[Research needed]" gaps, meaning the agent is expected to fetch and read untrusted third‑party content.