ui-test-cypress

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow for ui-test-cypress ingests the outsider’s free-text prompt to generate a Cypress testing plan (via the agent interface calling the skill with user-supplied “task/project context” text), so an attacker can inject instructions through that prompt input.