perplexity-search
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- CREDENTIALS_UNSAFE (SAFE): No hardcoded credentials were detected. The skill properly uses environment variables and includes a template with placeholders for the OpenRouter API key.- DATA_EXFILTRATION (SAFE): Network communication is restricted to authorized API endpoints for search functionality via the LiteLLM library.- EXTERNAL_DOWNLOADS (LOW): The skill requires the 'litellm' Python package, which is a standard library for LLM service integration.- COMMAND_EXECUTION (SAFE): The functionality to save results to a local file is user-controlled via CLI arguments and contains no unsafe execution logic.
Audit Metadata