canvas-design
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected in the instructions or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts to influence creative designs. While it lacks explicit boundary markers for this input, the attack surface is minimal as the output is restricted to visual artifacts (PDF, PNG) and markdown files.
- [EXTERNAL_DOWNLOADS]: The skill mentions downloading fonts for design purposes but refers to local paths within the skill's repository (
canvas-fonts/). No unverifiable remote code or suspicious third-party dependencies are referenced. - [COMMAND_EXECUTION]: No shell commands, subprocess calls, or system-level modifications are present in the provided instructions. The skill focuses on high-level design reasoning rather than system automation.
Audit Metadata