gourmet-research
Warn
Audited by Snyk on May 5, 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 requires fetching and extracting content from public review/listing sites (e.g., Google Maps, Tabelog, Yelp, TripAdvisor, OpenRice, Naver/Kakao Maps) — including using Playwright to load pages — and it uses those user-generated sources to drive evidence, scoring, and final decisions, so untrusted third-party content can materially influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata