web-search
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No obfuscation, hardcoded credentials, or unauthorized command executions were detected.
- [SAFE]: The skill defines a protocol for processing external search data with a safety-oriented 'snippets only' gate, which reduces the risk of the agent being misled by instructions found in search results (indirect prompt injection surface).
Audit Metadata