canvas-design
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of design instructions for an AI agent.
- [PROMPT_INJECTION]: While the skill uses strong directive language (e.g., 'CRITICAL', 'IMPORTANT') and simulates conversational history to influence output quality, these are standard prompt engineering techniques used to achieve the skill's creative goals and do not attempt to bypass safety guardrails or hijack agent behavior.
- [DATA_EXFILTRATION]: No network operations or sensitive file access patterns were detected.
- [REMOTE_CODE_EXECUTION]: The skill does not contain any commands to download or execute external code.
- [OBFUSCATION]: No hidden or encoded content was found in the provided files.
Audit Metadata