gemini-enterprise
Warn
Audited by Snyk on May 6, 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 ingests and queries third-party content—e.g., "Website | URL crawl | PUBLIC_WEBSITE" in SKILL.md/references and the SearchService/StreamAssist and ADK integration sections (SearchService, streamAssist, DiscoveryEngineSearchTool, and GCS/website import instructions) which cause the agent to read and act on public/untrusted web or external document sources—so untrusted content can materially influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata