ux-audit-walkthrough
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 explicitly calls
capture_screenshot(sendToLLM=true)to feed the live page’s visual context into the agent’s LLM, which can include outsider-authored free text from the target webpage (public web content) at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata