delegate-task

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

• Third-party content exposure detected (high risk: 0.90). The skill's Agent Configurations list public web tools ("brave-search", "web-fetch") and the Multi-Agent Workflow/usage examples explicitly instruct the research agent to "look at open source projects" and return research.response that is passed to other agents, so arbitrary public web content is ingested and can materially influence subsequent actions.