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's SKILL.md and references/frameworks.md explicitly describe and implement researcher/agent nodes that perform web search, browsing, and document retrieval (e.g., researcher_node calls perform_research and swarm agents list tools [search, browse, read]), so agents are expected to ingest and act on open/public third‑party content which can influence routing, decisions, and outputs.