The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/with_server.py utility uses subprocess.Popen with shell=True to execute server startup commands provided via arguments. This is intended to support shell features like directory changes (cd) and command chaining (&&) required for starting local development servers.
[DYNAMIC_EXECUTION]: The skill instructs the agent to generate and run Playwright scripts to perform automated browser interactions. This dynamic script creation is a core part of the skill's functionality for testing web applications.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from web applications, which creates a surface for indirect prompt injection.
Ingestion points: The agent retrieves rendered HTML, element selectors, and console logs from the browser environment.
Boundary markers: The example scripts do not include explicit markers or warnings to distinguish between the application's data and the agent's instructions.
Capability inventory: The skill has access to shell command execution (via the server helper) and file system writes (for screenshots and logs).
Sanitization: No data sanitization is performed on content retrieved from the web pages before it is processed by the agent.

webapp-testing