progressive-hint-ladder
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and system prompts for an AI agent to act as a learning coach.
- [SAFE]: No external dependencies, package installations, or remote scripts are referenced or executed.
- [SAFE]: There are no network operations, file system access commands, or credential handling detected.
- [PROMPT_INJECTION]: The system prompt uses instructional markers like 'NEVER' and 'IMPORTANT' to enforce pedagogical boundaries (e.g., preventing the AI from giving direct answers), which is benign and aligned with the skill's primary educational purpose.
- [DATA_EXPOSURE]: No hardcoded secrets or sensitive paths were found. The skill operates on user-provided educational problems and context.
Audit Metadata