The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/with_server.py uses subprocess.Popen with shell=True to start local development servers and subprocess.run to execute automation commands. This allows the agent to run setup commands like npm run dev or cd backend && python server.py. This functionality is the primary purpose of the script for managing test environments.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and process untrusted data from web applications.
Ingestion points: The agent is instructed to read rendered DOM content via page.content() (SKILL.md) and capture browser console messages (examples/console_logging.py).
Boundary markers: No specific delimiters or safety warnings are implemented to separate external web content from the agent's instructions.
Capability inventory: The skill possesses the capability to execute shell commands through the with_server.py utility and write to the local file system as seen in the example scripts.
Sanitization: There is no evidence of sanitization, filtering, or escaping of the web content or console logs before they are processed by the agent.
[DYNAMIC_EXECUTION]: The skill facilitates the execution of shell commands and Playwright automation scripts that are constructed or specified by the agent at runtime to fulfill testing tasks.

webapp-testing