desearch-web-search
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a web search interface for the Desearch API. It uses the
DESEARCH_API_KEYenvironment variable for authentication, which is a standard and safe practice for secret management in AI agent skills. The network operations are limited to the vendor's official domain (api.desearch.ai), and the script handles API responses and errors appropriately without any dynamic execution or data exfiltration risks. No indicators of prompt injection, obfuscation, or persistence mechanisms were found.
Audit Metadata