canvas-design
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [CREDENTIALS_UNSAFE] (SAFE): No hardcoded credentials or sensitive secrets were found in the skill metadata or code snippets.
- [EXTERNAL_DOWNLOADS] (SAFE): The skill does not attempt to download files or execute scripts from remote sources.
- [REMOTE_CODE_EXECUTION] (SAFE): No remote code execution patterns or piped shell commands are present.
- [COMMAND_EXECUTION] (SAFE): The code provided uses standard libraries for image generation and does not execute arbitrary shell commands.
- [DATA_EXFILTRATION] (SAFE): No network operations or patterns for sending data to external domains were identified.
- [PROMPT_INJECTION] (SAFE): The instructions follow a creative workflow and do not include bypass markers or attempts to override agent safety protocols.
Audit Metadata