three-part-lesson-designer
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, code execution, or data exfiltration attempts were detected. The skill is composed entirely of markdown instructions and metadata.
- [NO_CODE]: The skill does not include any scripts (.py, .js, .sh), binaries, or external dependencies. It relies purely on the AI's internal reasoning to generate lesson plans based on provided text inputs.
- [PROMPT_INJECTION]: The instructions are focused on pedagogical guidelines (Montessori principles). There are no attempts to override safety filters, extract system prompts, or induce unrestricted behavior.
- [DATA_EXFILTRATION]: There are no commands or functions that access the file system, environment variables, or perform network requests. The skill is entirely self-contained.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests user-provided text for 'Concept to teach' and 'Concrete materials', it does not have any dangerous capabilities (like code execution or web browsing) that could be abused via malicious input. The risk is limited to generating biased or incorrect educational content, which is a standard LLM limitation rather than a security vulnerability.
Audit Metadata