The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/with_server.py executes arbitrary shell commands provided through CLI arguments using subprocess.Popen(shell=True) and subprocess.run(). This is intended for starting development servers and running test scripts but lacks input validation.
[DYNAMIC_EXECUTION]: The skill instructions direct the agent to generate and execute custom Playwright scripts at runtime, facilitating a dynamic code execution workflow.
[INDIRECT_PROMPT_INJECTION]: The skill handles external web content, creating an attack surface for indirect prompt injection.
Ingestion points: Retrieves page content and screenshots via Playwright (e.g., examples/element_discovery.py).
Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its own logic and content retrieved from the web.
Capability inventory: The skill can execute shell commands and navigate to arbitrary URLs.
Sanitization: There is no mechanism to sanitize or validate external content before it is processed by the agent.

webapp-testing