cuihuo-diagnosis
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or technical vulnerabilities were detected. The skill operates entirely within the scope of a text-based interaction.
- [NO_CODE]: The skill consists purely of instructions for the AI agent to follow. It does not include scripts, binaries, or configuration files that execute commands or manage dependencies.
- [PROMPT_INJECTION]: While the skill contains strong instructions to maintain a specific diagnostic persona ("犀利模式"), it does not attempt to bypass underlying AI safety filters or override system-level constraints.
- [DATA_EXFILTRATION]: There are no network requests, API calls, or URL references that could be used to exfiltrate data.
- [REMOTE_CODE_EXECUTION]: No patterns for remote code execution, package installation, or dynamic script loading are present.
Audit Metadata