The Agent Skills Directory

[SAFE]: The skill follows security best practices for credential management by instructing the agent to use cy.env() for secrets instead of hardcoding them.
[SAFE]: External references are limited to official Cypress documentation and CLI tools.
[COMMAND_EXECUTION]: The skill specifies running npx cypress --version to determine the environment configuration, which is a standard and safe operation for a testing tool.
[SAFE]: Indirect prompt injection surface exists as the skill reads project configuration and existing test files to inform its output. Ingestion points: existing spec files and project config. Boundary markers: absent. Capability inventory: Read and Edit tools. Sanitization: absent. This is consistent with the primary purpose of a code-generation agent.

cypress-author