The Agent Skills Directory

[COMMAND_EXECUTION]: The helper script scripts/with_server.py utilizes subprocess.Popen with shell=True to execute server startup commands provided via the --server command-line argument. It further uses subprocess.run to execute a subsequent automation command.
[INDIRECT_PROMPT_INJECTION]: The skill implements an ingestion surface for untrusted external data by reading rendered DOM content, element text, and browser console logs (e.g., in examples/element_discovery.py and examples/console_logging.py).
Ingestion points: DOM content via page.content(), element attributes via get_attribute(), and console messages via page.on("console", ...).
Boundary markers: None identified in the instructions to the agent to treat external content as data only.
Capability inventory: Execution of arbitrary shell commands via scripts/with_server.py and local file writes in the example scripts.
Sanitization: No explicit sanitization or filtering of the ingested web content is performed before the agent processes it.
[DYNAMIC_EXECUTION]: The skill's primary workflow involves the agent dynamically generating and executing Python scripts using the Playwright library to automate browser interactions.

webapp-testing