The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/with_server.py utilizes subprocess.Popen with shell=True to launch local servers. This behavior is necessary for the skill's purpose of testing applications that require active server processes.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it reads and interacts with external web content.
Ingestion points: Data is ingested from web pages in examples/element_discovery.py and examples/console_logging.py via Playwright locators.
Boundary markers: No specific delimiters or safety instructions are used to separate web content from agent instructions.
Capability inventory: The skill can execute shell commands through the with_server.py script and write to the filesystem.
Sanitization: There is no evidence of content sanitization for data retrieved from the browser DOM.

webapp-testing