ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto download and execute several utility packages from the npm registry, includinggetdesign,skillui,impeccable, andplaywright. These tools are used for design token management, UI component inspiration, design auditing, and visual regression testing. - [COMMAND_EXECUTION]: The skill instructions involve executing shell commands to perform automated tasks such as capturing screenshots with Playwright, running static analysis on components with
impeccable, and fetching design configurations based on brand archetypes. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it ingests and processes content from external reference URLs.
- Ingestion points: Phase 1 includes
npx skillui --url <url>where the agent visits a user-provided or reference URL (SKILL.md). - Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore potential commands embedded within the reference website's content.
- Capability inventory: The skill has the capability to write React component files, execute shell commands via npx, and read local project files like
DESIGN.md(Phase 1, 3, 4, 5). - Sanitization: No sanitization or filtering logic is mentioned for the content retrieved from external URLs before it influences the agent's workflow.
Audit Metadata