perplexity-sdk-patterns

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides implementation templates and coding standards for developers integrating Perplexity AI search capabilities into their applications. All functionality is consistent with its stated purpose.
  • [EXTERNAL_DOWNLOADS]: The instructions guide users to install the official openai package using standard package managers (npm, pip). These are well-known and official libraries for the task.
  • [COMMAND_EXECUTION]: The code snippets demonstrate standard API interactions with the official Perplexity service endpoint (https://api.perplexity.ai) and do not perform any unauthorized or dangerous local command execution.
  • [CREDENTIALS_SAFE]: The skill correctly avoids hardcoding secrets, instead demonstrating the use of environment variables (PERPLEXITY_API_KEY) for secure API key management.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 07:55 AM
Security Audit — agent-trust-hub — perplexity-sdk-patterns