gaokao-science-tutor
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): No malicious patterns detected. The skill consists entirely of instructional text and metadata.
- [NO_CODE] (SAFE): The skill contains no executable scripts (Python, JS, Shell, etc.). It relies entirely on the LLM's natural language processing capabilities.
- [PROMPT_INJECTION] (SAFE): No evidence of system prompt extraction, bypass markers, or role-play jailbreaks. The 'teacher' persona is a benign instructional framework.
- [DATA_EXFILTRATION] (SAFE): No network operations, hardcoded credentials, or sensitive file path access detected.
- [EXTERNAL_DOWNLOADS] (SAFE): The README mentions a GitHub repository (flysheep-ai/education-skills) for installation instructions, which is a standard practice and involves manual user action (git clone) rather than automated execution.
Audit Metadata