Skills
skills/frostfoe7/rdz/ui-ux-pro-max/Gen Agent Trust Hub

ui-ux-pro-max

Warn

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local Python scripts (scripts/search.py, scripts/design_system.py) to query design guideline databases and generate markdown-based documentation for project design systems.
  • [DATA_EXFILTRATION]: The persist_design_system function in scripts/design_system.py constructs filesystem paths using the project_name and page parameters. These inputs are converted to lowercase and spaces are replaced, but the script fails to sanitize directory traversal sequences (such as ../). This vulnerability could be exploited to write files to unintended locations on the local system if the agent is provided with a malicious project name.
  • [PROMPT_INJECTION]: The data/design.csv and data/draft.csv files contain sections formatted as "System Prompt" or "Implementation Instructions for AI". These sections provide an indirect prompt injection surface where instructions intended to guide the agent's behavior are processed as data, potentially allowing for behavioral overrides.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 7, 2026, 03:42 PM
Security Audit — agent-trust-hub — ui-ux-pro-max