perplexity
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists exclusively of instructional documentation and usage guidelines for existing Perplexity AI tools.
- [SAFE]: No executable code, shell scripts, or external dependencies are included in the skill files.
- [SAFE]: The instructions prioritize resource management by recommending conservative limits on search results and tokens to prevent context bloat.
- [SAFE]: The skill includes explicit prohibitions against expensive or unnecessary tool calls, favoring more efficient alternatives like specialized MCPs or the researcher agent.
Audit Metadata