policy-risk-scanner
Warn
Audited by Snyk on Jul 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: 0.85). The required workflow includes “URL Mode” that crawls and analyzes all site content (and may download/scan files), meaning the agent will ingest outsider-authored free text from a user-supplied external website/URL into the LLM context at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata