canvas-design
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No attempts to override agent instructions or bypass safety filters were detected. The skill uses natural instructional language consistent with its purpose.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or sensitive credentials were found in the skill metadata or code snippets.
- [DATA_EXFILTRATION]: No network operations or patterns associated with data exfiltration were identified. The skill performs local file operations related to image saving.
- [COMMAND_EXECUTION]: The provided Python snippets use standard, well-known libraries (PIL/Pillow, Cairo, svgwrite) for their intended purposes without any unsafe subprocess calls or shell execution.
- [EXTERNAL_DOWNLOADS]: The skill does not attempt to download external scripts or execute remote code.
Audit Metadata