research-coordinator

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 2 sub-agent prompt in SKILL.md explicitly tells sub-agents to "Use the available tools to search for up-to-date, high-quality sources" and to return reports listing Title, meaning the agents will fetch and consume open/public web content (potentially user-generated) that is then read and synthesized and can change subsequent actions.