revision-coordinator

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow and dispatch templates explicitly instruct the agent to fetch and use external literature and full-text materials (e.g., "peer-reviewer skill simulates peer review using Zotero-sourced materials" and the "Additional Literature Search Dispatch" that runs OpenAlex queries), so it ingests untrusted public third‑party content which can influence routing and revision decisions.