The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/with_server.py utility executes shell commands provided as arguments to start and manage local development servers. It utilizes subprocess.Popen with shell=True to handle complex shell commands, which is a documented and intended feature for the tool's primary purpose of local web application testing.
[COMMAND_EXECUTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from web pages (DOM elements, console logs) that could theoretically influence the construction of shell commands by an agent.
Ingestion points: page.content() and page.locator().all() in element_discovery.py; console logs in console_logging.py.
Boundary markers: Not present; instructions do not provide explicit delimiters for external content.
Capability inventory: subprocess.Popen and subprocess.run are available in scripts/with_server.py to execute commands.
Sanitization: The skill does not implement specific sanitization of the extracted web content, relying on the user or agent to handle data appropriately.

webapp-testing