ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where user-supplied project and page names are used to construct file paths for the design system persistence feature. While the generated files are markdown-based and intended for documentation, the constructing logic in
scripts/design_system.pylacks thorough path sanitization, creating a potential surface for directory traversal. - Ingestion points: User-provided query and project/page names in
scripts/search.py. - Boundary markers: None; inputs are directly interpolated into file path strings.
- Capability inventory: Filesystem write access in
scripts/design_system.pyto create thedesign-system/directory structure and markdown files. - Sanitization: Basic replacement of spaces with dashes and lowercase conversion is performed, but navigation sequences such as
../are not filtered. - [EXTERNAL_DOWNLOADS]: The
SKILL.mdfile provides environment setup instructions that include commands to install Python using trusted system package managers such asbrew,apt, andwinget. - [COMMAND_EXECUTION]: The skill operates by running local Python scripts (
scripts/search.py,scripts/design_system.py) to provide its features. These scripts process the included CSV data files and do not perform network requests or execute arbitrary commands based on untrusted input.
Audit Metadata