web-testing-cypress-e2e

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes patterns for automated browser interaction, which involves processing external content from web pages and components.
  • Ingestion points: cy.visit() (SKILL.md, core.md), cy.mount() (SKILL.md, component-testing.md), and cy.intercept() (intercept.md) ingest external HTML, JavaScript, and API responses into the agent's context.
  • Boundary markers: The skill does not prescribe specific delimiters or "ignore" instructions for the content of the application under test, which is standard for E2E testing frameworks.
  • Capability inventory: The skill documents the use of cy.task() for Node.js execution (custom-commands.md) and cy.exec() for shell command execution (reference.md, ci.md), which are powerful capabilities if used to process untrusted data.
  • Sanitization: No specific sanitization or escaping of the application's DOM or API responses is described before processing by assertions or custom tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 03:57 PM
Security Audit — agent-trust-hub — web-testing-cypress-e2e