ui-ux-governance
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data that influences high-capability agent tasks, creating a surface for indirect prompt injection.\n
- Ingestion points: Instructions in
SKILL.mdrequire the agent to read "existing requirement/design/component evidence", "tool output", and "external references" from the project environment.\n - Boundary markers: The instructions lack explicit delimiters or warnings to disregard instructions that may be embedded within the ingested data.\n
- Capability inventory: The skill binds its findings to sensitive lifecycle tasks such as
writing-plans,executing-plans, andrequesting-code-review.\n - Sanitization: There are no instructions to sanitize or validate the external content before it is processed and used to guide implementation and review steps.\n- [EXTERNAL_DOWNLOADS]: The skill references documentation and guidelines from external sources.\n
- The skill includes links to official UI/UX and accessibility standards from the World Wide Web Consortium (W3C) and the UK Government (GOV.UK).\n
- The skill provides references to official documentation for the Playwright testing framework for visual and accessibility verification.
Audit Metadata