perplexity
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlcommands to interact with the Perplexity API. This is the intended primary purpose of the skill and uses standard implementation patterns. - [EXTERNAL_DOWNLOADS]: The skill makes network requests to
api.perplexity.ai. Perplexity is a well-known service, and these operations are documented neutrally as part of the skill's core functionality. - [DATA_EXFILTRATION]: User queries are sent to the Perplexity API. This is the legitimate purpose of an AI search skill and targets an established service provider.
- [CREDENTIALS_UNSAFE]: The skill correctly instructs users to store sensitive API tokens in environment variables (
PERPLEXITY_TOKEN) rather than hardcoding them in scripts.
Audit Metadata