agent-sdk
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: 0.80). The skill explicitly exposes WebSearch/WebFetch capabilities (see "Built-in capabilities: Web search
- Access real-time information" and the "Tool Mapping" entry "Web Search | WebSearch, WebFetch"), meaning the agent can fetch and read arbitrary public web content which is untrusted and can be interpreted at runtime, enabling indirect prompt injection.
Audit Metadata