frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: LOW
Full Analysis
- PROMPT_INJECTION (SAFE): The skill uses instructional keywords like 'CRITICAL' and 'IMPORTANT' to emphasize design principles such as typography and spatial composition. These are used for creative direction and do not attempt to override the model's core safety instructions or extract system prompts.
- DATA_EXFILTRATION (SAFE): No patterns related to credential exposure, network requests (curl, wget), or access to sensitive file paths were identified.
- COMMAND_EXECUTION (SAFE): The skill is purely documentation-based and does not include any shell commands, subprocess calls, or scripts that would interact with the host operating system.
- EXTERNAL_DOWNLOADS (SAFE): No external dependencies, package installations (npm, pip), or remote code execution patterns are present. While it mentions the 'Motion library', it does so as a creative suggestion for the agent's output rather than a skill-level dependency.
Audit Metadata