intent-confirmation
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely informational and procedural. It establishes a 'confirm-before-execute' workflow to improve reliability and prevent misinterpretation of user requests.
- [SAFE]: No evidence of prompt injection or malicious instructions was found. The core logic promotes safety by requiring explicit user confirmation for complex tasks.
- [SAFE]: The skill does not perform any network operations, file system access, or credential handling. It only references a single benign tool, 'AskUserQuestion'.
- [SAFE]: No obfuscation, dynamic code execution, or persistence mechanisms are present in the provided content.
Audit Metadata