web-search
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 uses the agent's built-in WebSearch to fetch and read arbitrary public web results and instructs the agent to cite and synthesize content from those URLs, which exposes it to untrusted third-party web content that could carry indirect prompt injection.
Audit Metadata