ux-web-review
Warn
Audited by Snyk on Jul 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow can ingest outsider-authored free text at runtime when it instructs the agent to “Navigate to the URL using browser tools” and then analyze/capture page content (public web content fetched at runtime becomes LLM-readable prose/screen text).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata