izakaya-search

Warn

Audited by Snyk on Feb 27, 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's required workflow (SKILL.md Steps 2–3 and the Google Maps fake review detection) explicitly performs WebSearch/WebFetch of public gourmet sites and Google Maps and parses user-generated reviews (untrusted third-party content) to adjust scores and drive recommendations, so external page content can materially influence the agent's decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 06:19 AM