The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/with_server.py utility uses subprocess.Popen with shell=True to start web servers based on commands provided as command-line arguments. This allows for the execution of arbitrary shell commands as part of the server management workflow.
[COMMAND_EXECUTION]: The skill's primary function involves the agent dynamically generating and executing Python scripts using the Playwright library to interact with local or remote web applications.
[COMMAND_EXECUTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to ingest and analyze untrusted DOM content and screenshots from web applications.
Ingestion points: Data enters the agent's context through page.content() (referenced in SKILL.md), page.screenshot(), and DOM element discovery methods demonstrated in examples/element_discovery.py.
Boundary markers: The instructions in SKILL.md do not define clear boundaries or provide warnings to ignore instructions found within the processed web content.
Capability inventory: The agent possesses the capability to execute shell commands via scripts/with_server.py and run arbitrary Python code on the host environment.
Sanitization: There is no evidence of sanitization, filtering, or validation of the ingested web content before it is analyzed and acted upon by the agent.

webapp-testing