The Agent Skills Directory

[COMMAND_EXECUTION]: The helper script scripts/with_server.py uses subprocess.Popen with shell=True to execute server commands provided via the --server argument. This allows for the execution of arbitrary shell logic, including command chaining.
[COMMAND_EXECUTION]: The same script executes the main automation command using subprocess.run. While this does not use a shell, the arguments are dynamically provided by the agent.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.
Ingestion points: The agent ingests data from external web pages and console logs in examples/element_discovery.py and examples/console_logging.py.
Boundary markers: No explicit markers or instructions are provided to the agent to ignore or isolate instructions found within the scraped data.
Capability inventory: The skill provides a mechanism for shell command execution through the scripts/with_server.py script.
Sanitization: No sanitization or validation is performed on the content retrieved from web pages before it is used by the agent to determine subsequent steps.

webapp-testing