gemini
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: 0.90). The skill explicitly supports "Web Search with Synthesis" and "News Lookup" and gives examples like "Search and synthesize: [query]" and "Latest news about: [topic]," which indicates it will fetch and ingest open/public web/news content (untrusted third‑party sources) for the agent to read and synthesize.
Audit Metadata