qa-cypress-writer

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill generates executable Cypress tests from test case specifications provided by external Phase 2 tools, creating a surface for indirect prompt injection attacks.
  • Ingestion points: Test specifications are read from tools such as qa-testcase-from-docs, qa-manual-test-designer, and qa-browser-data-collector as defined in the SKILL.md workflow.
  • Boundary markers: The instructions do not define any delimiters or provide guidance for the agent to distinguish between its own logic and the untrusted data within the test cases.
  • Capability inventory: The skill has the capability to write executable TypeScript files (.cy.ts, .cy.tsx), create custom commands in support/commands.ts, and modify global configuration in cypress.config.ts.
  • Sanitization: There is no evidence of input validation, escaping, or sanitization to prevent the injection of malicious Cypress commands (e.g., cy.request(), cy.readFile()) into the generated test files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:38 PM
Security Audit — agent-trust-hub — qa-cypress-writer