swarm-spawning

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly enables agents to use WebFetch and WebSearch (see "Built-in Agent Types" -> "claude-code-guide") and includes research/design agent workflows that fetch external URLs and documentation (e.g., "Research current best practices", "Compare implementation with Figma at [URL]"), so the agent will fetch and interpret untrusted third‑party web content that can influence its actions.