research-guide
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: 1.00). The skill explicitly instructs using the /sc:research command to fetch and synthesize web research and includes a References section with URLs, which means the agent will retrieve and interpret open/public third-party web content (untrusted user-generated sources).
Audit Metadata