ux-critique
Warn
Audited by Snyk on Jul 13, 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 when it “walk[s] the flow” via
agent-browseron a “Live URL / running app” (public web content / arbitrary pages), whose extracted page text is read into the LLM context during runtime navigation and extraction.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata