deep-question
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
exectool to run thedeeptutorbinary, which is the primary mechanism for generating quizzes. User inputs are wrapped in double quotes within the command templates to manage shell boundary separation. - [SAFE]: No obfuscation, data exfiltration, or unauthorized prompt injection patterns were detected. The skill requires the
deeptutorbinary as declared in its metadata, which is consistent with its stated purpose.
Audit Metadata