ui-ux-design

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of auditing and editing UI code.
  • Ingestion points: Files processed via Read, Grep, and Glob, as well as web content retrieved through mcp_playwright_browser_navigate in SKILL.md.
  • Boundary markers: There are no defined delimiters or 'ignore' instructions to separate untrusted data (like audited source code or web text) from system instructions.
  • Capability inventory: The skill possesses Edit and Write capabilities, allowing it to modify the local filesystem based on potentially malicious instructions found in analyzed data.
  • Sanitization: No logic is present to sanitize or validate external content before it is processed by the agent.
  • [NO_CODE]: The skill contains only Markdown instructions and reference materials (SKILL.md, reference.md). It does not ship with executable script files or install external packages.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:24 AM