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, andGlob, as well as web content retrieved throughmcp_playwright_browser_navigateinSKILL.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
EditandWritecapabilities, 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