orchestrating-swarms

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

• Third-party content exposure detected (high risk: 0.90). The skill enables agents to fetch and ingest arbitrary public web content — e.g., the claude-code-guide agent lists WebFetch and WebSearch tools, research agents (best-practices-researcher, framework-docs-researcher) are explicitly described to gather external documentation/best-practices, and the design agent example references a Figma URL — so the agent will read untrusted third-party content as part of its workflow.