skills/garethmanning/education-agent-skills/checking-for-understanding-protocol-designer/Gen Agent Trust Hub
checking-for-understanding-protocol-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a pure prompt extension without any executable code, scripts, or binary files. It relies entirely on the AI model's internal reasoning to generate text based on provided educational principles and research foundations.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for ingesting untrusted user input (e.g., lesson content, student profiles) that is interpolated into the model's prompt. This is evaluated as safe because the skill lacks any capabilities (such as network access, file writing, or tool execution) that could be exploited via malicious instructions in the data.\n
- Ingestion points: Input fields defined in SKILL.md (lesson_content, student_profiles, common_misconceptions, student_level).\n
- Boundary markers: Absent. The prompt does not use delimiters or instructions to ignore embedded commands in the input.\n
- Capability inventory: None. The skill does not invoke any tools or external scripts and has no access to the file system or network.\n
- Sanitization: Absent. Input is used as-is for prompt interpolation.
Audit Metadata