ui-ux-audit
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a potential attack surface for indirect prompt injection.
- Ingestion points: The skill is instructed to audit "code or live page" and "run the app / Playwright screenshot", meaning it ingests content from local files and remote URLs provided by the user.
- Boundary markers: The instructions do not define explicit boundary markers or delimiters to separate the UI content being audited from the agent's primary instructions.
- Capability inventory: The skill has the capability to "APPLY the fixes", which involves writing to the file system to modify the application's source code.
- Sanitization: There are no explicit instructions for the agent to sanitize or ignore potential instructions embedded within the HTML, CSS, or ARIA attributes of the interface being audited.
Audit Metadata