perplexity-deep-research

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: API credential management is handled securely via the PERPLEXITY_API_KEY environment variable, avoiding hardcoded secrets or unsafe storage practices.
  • [SAFE]: The skill communicates with the official and well-known Perplexity AI API endpoint (api.perplexity.ai).
  • [SAFE]: The provided Python script uses only the standard library (urllib, json, argparse), which eliminates supply chain risks associated with third-party packages.
  • [SAFE]: Although the skill processes untrusted user input for research queries, it mitigates injection risks by properly serializing the input into a JSON structure using the standard json.dumps function before transmission.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 04:52 AM
Security Audit — agent-trust-hub — perplexity-deep-research