ux-polish
Warn
Audited by Snyk on Nov 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow has the agent screenshot or inspect a UI at runtime (SKILL.md:34), which can pull in page text from an arbitrary or user-supplied URL, so outsider-authored content on that page could reach the agent only if it actively browses it.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata