Agent Orchestrator
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's MCP/Tool Access and Content Creation Pipeline explicitly reference using Firecrawl and Playwright for "Research" to "Gather sources" and "Extract key information" from external web sources, meaning agents will fetch and interpret untrusted public content (open web/user-generated) as part of workflows.
Audit Metadata