ui-research

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to search, collect, and analyze examples from public web sources (Phase 2 "Search Strategy" and Phase 3 "Collect", naming sites like Mobbin, Land-book, Dribbble, Awwwards, Pinterest and saving URLs), which are untrusted third‑party pages the agent would read and interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 10:37 AM