token-efficiency
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly recommends and demonstrates performing WebSearches and parallel literature/web queries (see "Efficient Scientific Literature Searches" / "WebSearch" examples) and expects the agent to read and interpret those external public search results, which are untrusted third‑party content.
Audit Metadata