multi-agent-patterns

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly describes agents performing "web search, document retrieval" (Example 1: Research Team Architecture) and discusses "searching multiple independent sources" in the Parallelization Argument, which indicates the system expects agents to fetch and read open/public web content that can influence downstream tool use and decisions.