ui-audit
Warn
Audited by Snyk on Jun 23, 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). Skill runtime path: it instructs the agent to render a user-supplied Live URL / fetch pages and then run
scripts/ui_checks.jsin the browser, which reads arbitrary outsider-authored page text/DOM (including any third-party content on that page) into the LLM context via the returned JSON leads (e.g.,rawI18nKeys,technicalGarbage,overflowingText,lowContrastText).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata