perplexity
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional documentation and usage guidelines for Perplexity AI MCP tools. It does not contain any executable scripts, shell commands, or network-active code.
- [SAFE]: The instructions promote security and resource efficiency by explicitly prohibiting expensive tools (perplexity_research) and recommending conservative search limits (max_results: 3) to prevent context bloat.
- [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The skill correctly directs the agent to specialized tools (Context7, Graphite, Nx) for specific tasks, following a defined tool selection chain.
Audit Metadata