gemini
Warn
Audited by Snyk on Feb 16, 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 includes real-time "Search Grounding" (examples using "tools": [{"google_search": {}}] and "Image Generation with Search Grounding") which fetches and ingests open web search results and their groundingMetadata, exposing the agent to untrusted third-party web content that could contain indirect prompt injection.
Audit Metadata