The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external test files which could contain malicious instructions designed to exploit the migration process.
Ingestion points: Reads Cypress and Selenium test files from the local filesystem.
Boundary markers: No explicit safety delimiters are used to separate untrusted source code from agent instructions.
Capability inventory: Can execute shell commands and modify filesystem content.
Sanitization: Source content is processed without specific security validation.
[DYNAMIC_EXECUTION]: The skill creates new test scripts and executes them via the Playwright CLI to verify conversion success, representing the execution of dynamically generated code.
[COMMAND_EXECUTION]: Uses npx to run tests and initialize frameworks, which is a standard but powerful capability that interacts with external package registries.

migrate