The Agent Skills Directory

[COMMAND_EXECUTION]: The helper script scripts/with_server.py utilizes subprocess.Popen with shell=True to execute server start commands provided as arguments. It also uses subprocess.run to execute automation commands. This pattern allows for arbitrary shell command execution on the host system, which is the intended mechanism for the skill to manage local development environments.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted data from web applications.
Ingestion points: examples/element_discovery.py extracts text from DOM elements such as buttons, links, and inputs; examples/console_logging.py captures all browser console log messages.
Boundary markers: None. The skill does not implement delimiters or instructions to the agent to ignore embedded commands within the scraped web data.
Capability inventory: The agent has access to scripts/with_server.py for shell execution and standard file system operations for saving logs and screenshots.
Sanitization: No evidence of sanitization, escaping, or validation of the content retrieved from the browser before it is processed by the agent.

webapp-testing