design-ui-designer
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill provides legitimate design tools and documentation.
- [COMMAND_EXECUTION]: The skill includes Python scripts (
scripts/check_contrast.py,scripts/generate_css_tokens.py, andscripts/generate_tokens.py) designed for local execution. These scripts perform mathematical calculations (color contrast) and string transformations (CSS generation) using standard library components likeargparse,json, andcolorsyswithout spawning subprocesses or executing arbitrary commands. - [PROMPT_INJECTION]: All instructions in
SKILL.mdare focused on design workflows and task execution. There are no attempts to override agent instructions, bypass safety filters, or exfiltrate system prompts. - [DATA_EXFILTRATION]: No network operations, hardcoded credentials, or unauthorized file access patterns were found. The scripts strictly process command-line arguments and user-provided local JSON files.
- [EXTERNAL_DOWNLOADS]: The skill does not contain any remote code downloads or external package dependencies. All logic is contained within the provided scripts.
- [SAFE]: The JavaScript example provided in
references/tokens.mdis a standard implementation for a web-based theme switcher and does not pose a risk to the agent environment.
Audit Metadata