assistant-presets
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a documentation and implementation framework for assistant presets. It does not contain any executable scripts or instructions that pose a threat to the execution environment.
- [DATA_EXFILTRATION]: No evidence of unauthorized network requests, credential harvesting, or sensitive file access was found within the skill's instructions or code examples.
- [REMOTE_CODE_EXECUTION]: The provided TypeScript implementation is for structural guidance and does not include mechanisms for downloading or executing remote code.
- [PROMPT_INJECTION]: While the skill discusses system prompt creation, it does not include instructions designed to bypass agent safeguards or override the primary agent's behavioral constraints.
Audit Metadata