multi-agent-supervisor

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly includes a Browser Agent with "web_browsing" and "scraping" capabilities (see Agent Pool / Capabilities and dependencies listing web-scrape) and the supervisor lifecycle and routing steps state that agent outputs are read and used to drive routing, decisions, and subsequent actions, meaning it will ingest open/public third-party web content that could carry untrusted instructions.