perplexity-search
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements standard security practices for managing sensitive information. It correctly instructs users to use environment variables or .env files for storing API keys, which is a recognized safe practice for preventing credential exposure in code.
- [EXTERNAL_DOWNLOADS]: The skill utilizes 'litellm', a widely-recognized and trusted library for interacting with various LLM providers. All external references are directed toward OpenRouter (openrouter.ai), which is a well-known service in the AI ecosystem.
- [COMMAND_EXECUTION]: The provided Python scripts perform basic tasks such as checking environment variables and making API calls. There are no instances of unsafe command execution, subprocess spawning with untrusted input, or privilege escalation attempts.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes data from the web (via Perplexity search results), it is a standard search utility. It does not possess dangerous capabilities like arbitrary code execution or sensitive file writes that could be exploited by malicious content retrieved during a search.
Audit Metadata