ai-native-cli
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of technical documentation and design rules for developers. It does not contain any executable code or malicious logic.
- [CREDENTIALS_UNSAFE]: No hardcoded credentials or secrets were found. The spec explicitly defines guardrails (Rule G2, G3) to detect and reject API keys and sensitive file paths in CLI arguments.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns or unauthorized downloads were identified. The mentioned GitHub URL is for reference purposes and points to a repository for the spec itself.
- [OBFUSCATION]: The content is provided in plain markdown with no detected use of Base64, zero-width characters, homoglyphs, or other obfuscation techniques.
- [PROMPT_INJECTION]: The instructions are clear and technical, with no attempts to override agent behavior, bypass safety filters, or extract system prompts.
Audit Metadata