google-cloud-agent-sdk-master
Warn
Audited by Snyk on Mar 18, 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's references/SKILL.full.md explicitly enables WebFetch/WebSearch and shows RAG/ADK agents (e.g., using web_search_tool, VectorSearchTool and public targets like GitHub/codelabs/cloud.google.com) that "retrieve relevant docs automatically" and use that content to drive generation, so untrusted public web content could materially influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata