ui-check-framework

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): The skill defines a framework that ingests data from external web environments, which is a surface for indirect prompt injection. \n
  • Ingestion points: The skill interacts with web pages to discover data-qa or data-testid elements and captures screenshots for layout and theme analysis. \n
  • Boundary markers: Not specified; the instructions do not include delimiters or warnings to ignore instructions embedded in the tested UI. \n
  • Capability inventory: The skill executes Playwright flows and manages scripts defined in package.json (e.g., ui:check, ui:watch). \n
  • Sanitization: Not specified; the instructions do not mention sanitizing content extracted from the DOM. \n- Safe (SAFE): No evidence of hardcoded credentials, malicious remote code execution (curl|bash), or unauthorized data exfiltration was detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 08:11 PM