The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/with_server.py is designed to execute arbitrary shell commands provided through its command-line interface.
It uses subprocess.Popen(cmd, shell=True) to launch development servers specified via the --server flag.
It uses subprocess.run(args.command) to execute the primary test suite command provided as the command remainder. This is the core intended functionality of the skill to support local development workflows.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it interacts with and captures data from external web applications during testing.
Ingestion points: The assets/playwright-examples/console_logging.py script captures all console output from the target web application using the page.on("console", ...) event handler.
Boundary markers: The scripts do not implement boundary markers or instructions to ignore potential commands embedded within the captured console logs or page content.
Capability inventory: The skill has the capability to execute shell commands (via scripts/with_server.py), perform network requests, and write files to the /tmp directory (via Playwright scripts).
Sanitization: There is no sanitization or filtering of the captured console messages before they are aggregated and written to the output file /tmp/console.log.

webapp-testing