create-e2e-tests
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the standard Cypress test runner using
npx cypress run. This is the primary intended function of the skill and does not involve unauthorized or hidden commands. - [DATA_EXPOSURE]: The skill involves reading local project files such as
cypress.config.tsand existing command files to understand the project structure. This access is scoped to the development environment and is required for the skill's operation. - [INDIRECT_PROMPT_INJECTION]: The skill reads external rule files (
e2e-tests-rules.mdc) and project source code which are then used to influence test generation. While this represents a surface for indirect injection if those project files were maliciously crafted, the risk is inherent to the task of code analysis and generation.
Audit Metadata