perplexity
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a standard interface for the Perplexity AI API. It uses 'urllib.request' to communicate with 'https://api.perplexity.ai' and provides a Typer-based CLI for research queries.
- [EXTERNAL_DOWNLOADS]: The skill fetches content from 'https://api.perplexity.ai'. This is the primary and expected function of the skill to provide web-grounded AI responses.
- [CREDENTIALS_UNSAFE]: The skill looks for 'PERPLEXITY_API_KEY' in environment variables or '.env' files. It does not contain hardcoded secrets. The documentation correctly instructs users to provide their own key.
- [COMMAND_EXECUTION]: The skill uses standard Python and Shell scripts ('run.sh', 'sanity.sh') to manage its environment via 'uv'. These scripts perform routine setup tasks like creating virtual environments and installing local dependencies.
Audit Metadata