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's SKILL.md and examples.md explicitly show agents ingesting open-web search results and documents (e.g., WebResearcher uses DuckDuckGoSearchRun and multiple agents call retriever(topic).passages) which the agents read and use to drive routing/decisions, exposing them to untrusted third-party content.