The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/with_server.py uses subprocess.Popen with shell=True to execute commands passed via the --server argument. This is intended to support complex command strings (e.g., cd backend && python server.py), but it allows the execution of arbitrary shell commands provided by the agent or user instructions.
[COMMAND_EXECUTION]: The scripts/with_server.py utility also uses subprocess.run to execute the final automation command provided as trailing arguments. If these arguments are not strictly controlled, they can lead to unintended command execution on the host system.
[DYNAMIC_EXECUTION]: The skill encourages the agent to dynamically generate and execute Python scripts using Playwright. While this is the primary purpose of the skill, the execution of agent-generated code inherently carries risks if the agent is influenced by malicious data during the script generation process.

webapp-testing