ai-coordinating-agents

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly invokes web search and retrieval of open-web passages (e.g., ResearchAgent uses self.retriever(topic).passages, the WebResearcher uses DuckDuckGoSearchRun via langchain tools, and a search_web tool is shown), so agents consume untrusted public web/social content which they then read and interpret.