The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using npx playwright test to verify converted test files at runtime.
[DYNAMIC_EXECUTION]: The agent generates new Playwright test scripts based on existing source files and subsequently executes these generated scripts to ensure they function correctly.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted code from local test files which could potentially contain malicious instructions aimed at the agent.
Ingestion points: The agent scans the cypress/ directory, package.json dependencies, and individual test files provided as arguments.
Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted code from the agent's instructions.
Capability inventory: The skill has the ability to execute shell commands (npx), write new files (converted tests), and delete existing files (cleanup step).
Sanitization: There is no evidence of sanitization or validation of the content within the source test files before they are converted or executed.

migrate