design

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's Phase 2 "Live Research" explicitly instructs the agent to use the Gemini CLI or WebSearch to fetch and ingest current open-web OSS library pages (GitHub/npm/public websites) and use those findings to choose libraries for the catalog, meaning untrusted third-party content is read and can materially influence subsequent decisions and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 02:02 AM