Agent Orchestrator

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly references using "General-Purpose + Firecrawl" to "gather sources" and "extract key information" in the Content Creation Pipeline example (and lists web-capable tools in MCP/Tool Access), which indicates the orchestrator will fetch and interpret public third‑party web content that can influence downstream agent actions.