onboarding-ux
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external web applications using browser tools (Playwright/Chrome MCP). This presents an indirect prompt injection surface where a malicious website could attempt to influence the agent's behavior or the code it generates during the audit and generation phases.
- Ingestion points: Browser tool output captured while navigating web application pages in the audit phase (e.g., list pages, dashboard, settings).
- Capability inventory: Writing generated UI components and audit reports to the local file system (
.jez/artifacts/), reading the project's codebase to match component patterns. - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between the analyzed web page content and its own internal instructions.
- Sanitization: The skill does not describe any sanitization, validation, or filtering of the content retrieved from the web browser before it is used to generate artifacts.
Audit Metadata