perplexity-ai

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and run the @useclawlink/cli package from the npm registry. This package is the primary interface for managing the integration as provided by the author.
  • [COMMAND_EXECUTION]: Shell commands are used via the @useclawlink/cli tool to perform authentication, connect to Perplexity AI, and execute specific API actions such as search and chat completions.
  • [DATA_EXPOSURE]: The tool stores authentication credentials locally in the user's home directory at ~/.clawlink/credentials.json to maintain session state, which is standard behavior for this CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:43 PM
Security Audit — agent-trust-hub — perplexity-ai