The Agent Skills Directory

[COMMAND_EXECUTION]: The utility script scripts/with_server.py uses subprocess.Popen(shell=True) and subprocess.run() to execute commands provided via command-line arguments, which is a significant capability that could be exploited if inputs are not properly sanitized.- [PROMPT_INJECTION]: The skill has a large attack surface for indirect prompt injection. It is designed to ingest and process untrusted data from web applications through page.content(), page.locator().all() in examples/element_discovery.py, and page.on("console", ...) in examples/console_logging.py. The absence of boundary markers or sanitization logic means malicious content on a tested site could attempt to manipulate the agent's behavior.- [COMMAND_EXECUTION]: The SKILL.md instructions guide the agent to dynamically generate and execute native Python Playwright scripts at runtime, facilitating the execution of locally-created code.

webapp-testing