critical-thinking-task-designer
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for curriculum design and pedagogical support. It lacks any functionality for file system access, network communication, or administrative operations.
- [PROMPT_INJECTION]: The skill uses a structured instructional prompt with a defined persona. It does not contain instructions to override system safety guidelines, nor does it attempt to leak system prompts or bypass restrictions.
- [REMOTE_CODE_EXECUTION]: There are no references to external scripts, package installations, or dynamic code execution modules. The skill does not use shell commands or subprocess calls.
- [DATA_EXFILTRATION]: The skill does not access sensitive local files (e.g., .ssh, .aws) or hardcoded credentials. It does not perform outbound network requests.
Audit Metadata