cuihuo-questioning
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely text-based and instructional. It focuses on facilitating a questioning process between the AI and the user without invoking external tools or scripts.
- [DATA_EXFILTRATION]: No network operations (such as curl, wget, or fetch) or sensitive file access patterns were detected. The skill only interacts with the user via standard chat input and output.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of external scripts. The skill does not use package managers or dynamic code execution functions like eval or exec.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or secrets were found. The skill does not request or handle sensitive environmental variables.
- [PROMPT_INJECTION]: The instructions provide a clear persona and behavioral constraints for the AI without attempting to bypass safety filters or override system-level instructions in a malicious way.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided "large questions" (untrusted data), it lacks dangerous capabilities (like filesystem access, shell execution, or internet browsing) that could be exploited through injection. The interaction is limited to text generation.
Audit Metadata