better-prompt
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely composed of Markdown and YAML configuration files. No executable scripts (Python, JavaScript, Shell, etc.) or compiled binaries are included, which eliminates categories related to malicious code execution.
- [SAFE]: There are no network-related commands or functions (such as curl, wget, or API requests) that would allow for data exfiltration or external downloads.
- [SAFE]: The skill does not request or access sensitive system resources, environment variables, or credential files. It operates strictly within the text-processing boundaries of the AI agent.
- [SAFE]: While the skill is designed to process and "optimize" untrusted user-supplied prompts (Indirect Prompt Injection surface), it possesses no functional capabilities—such as file writing or command execution—that could be exploited by malicious input. The risk is limited to the text output generated for the user.
- [SAFE]: No obfuscation, hidden characters, or suspicious metadata patterns were detected. All external references point to official documentation from trusted organizations including OpenAI and Anthropic.
Audit Metadata