skills/ui5/webcomponents/visual-test/Gen Agent Trust Hub

visual-test

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate documentation and code examples for creating visual tests within the UI5 project structure. It utilizes standard local import paths and references official vendor packages.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it generates test code based on user input.
  • Ingestion points: User-provided component names and descriptions (e.g., "add a visual spec for X") serve as the template for generated files.
  • Boundary markers: Absent; the instructions do not define delimiters or provide warnings to ignore embedded instructions within user-provided data.
  • Capability inventory: The skill's primary function is to guide the agent in writing executable Cypress spec files (.cy.tsx) to the local file system.
  • Sanitization: Absent; there are no explicit steps provided for the agent to sanitize or validate user input before it is interpolated into the generated source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 10:51 AM
Security Audit — agent-trust-hub — visual-test