The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/with_server.py is designed to execute arbitrary shell commands provided via arguments to start local development servers and run automation tasks. It utilizes subprocess.Popen with shell=True and subprocess.run to facilitate these operations, which is the primary intended functionality of the toolkit.
[PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by processing untrusted data from the web applications being tested.
Ingestion points: Browser console logs are captured in examples/console_logging.py using page.on("console", ...), and DOM content is read in examples/element_discovery.py using page.locator(...).all() and inner_text().
Boundary markers: Absent. The instructions and scripts do not provide delimiters or instructions to the agent to ignore potentially malicious commands embedded in the captured web content.
Capability inventory: The skill possesses the capability to execute shell commands through the scripts/with_server.py utility.
Sanitization: Absent. The captured web content and console logs are processed and stored in the output directory without validation or filtering for adversarial instructions.

webapp-testing