cognitive-load-theory
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses instructional steering to guide the agent's behavior in 'Coach mode' (e.g., using
[WAIT]markers for pacing). These instructions are standard for educational workflows and do not attempt to bypass safety filters or override system constraints. - [DATA_EXPOSURE]: No sensitive file paths, environment variables, or hardcoded credentials were found. The instructions focus on pedagogical analysis rather than system data access.
- [EXTERNAL_DOWNLOADS]: The skill references resources on the vendor's official domain (deciqai.com) and GitHub organization (github.com/deciqAI). These are recognized as legitimate vendor resources and do not involve the execution of untrusted external code.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided descriptions of learning scenarios, it does not possess dangerous capabilities (such as file writing, network requests, or shell execution). The risk of a user input influencing the agent to perform harmful actions is negligible in this context.
- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or dynamic execution patterns were detected in the skill instructions or examples.
Audit Metadata