multi-agent-patterns

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly describes and implements a "researcher" worker that uses web-facing tools (e.g., "web search, document retrieval" in SKILL.md Example 1 and the references/frameworks.md swarm example where create_agent("research", ..., tools=[search, browse, read]) is defined), which requires fetching and interpreting open/public third‑party content that can materially influence agent decisions and handoffs.