skills/garethmanning/education-agent-skills/sheltered-instruction-lesson-modifier/Gen Agent Trust Hub
sheltered-instruction-lesson-modifier
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely descriptive and instructional. It contains no executable scripts, shell commands, or external dependencies. All URLs in the frontmatter refer to established academic citations and recognized pedagogical models.
- [NO_CODE]: The skill operates entirely within the LLM's prompt context, using the provided instructions to transform text-based lesson plans into structured pedagogical outputs without invoking external tools or system-level functions.
- [PROMPT_INJECTION]: I analyzed the instructions for potential override attempts. The text uses instructional language ('It is important that...', 'Ensure...') to guide the model's output quality, which is legitimate and benign. There are no attempts to bypass safety guidelines or leak system prompts.
- [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or data exfiltration patterns were found. The skill processes user-provided lesson plans and returns educational strategies.
Audit Metadata