wxt
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions utilize 'npx wxt@latest' to initialize new projects from the WXT framework repository. This is a standard development practice for this well-known open-source tool.
- [COMMAND_EXECUTION]: The documentation includes standard shell commands for Node.js project management, such as 'npm install', 'npm run dev', and 'npm run build', which are required for the intended development workflow.
- [DATA_EXFILTRATION]: Code examples demonstrate sending data to the OpenAI API. As OpenAI is a well-known service and the data being sent (code diffs) is consistent with the skill's primary purpose of providing AI-powered code reviews, this is classified as safe functionality.
- [CREDENTIALS_UNSAFE]: The code correctly handles API keys by retrieving them from secure local extension storage ('storage.getItem') rather than hardcoding sensitive strings.
- [PROMPT_INJECTION]: The skill processes external data (GitHub pull request diffs) to provide AI summaries. While this represents a surface for indirect prompt injection, it is the primary function of the demonstrated tool and uses standard length-limiting sanitization ('slice(0, 5000)').
Audit Metadata