The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill interacts with external, untrusted content from web applications during the form discovery and testing process.
Ingestion points: The skill uses browser_snapshot to read the accessibility tree and form elements from the application under test in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore instructions embedded within the target application's text are provided.
Capability inventory: The skill possesses interaction capabilities including browser_fill, browser_fill_form, and browser_press to manipulate the target application, and reads browser_console_messages and browser_network_requests in SKILL.md.
Sanitization: There is no mention of sanitizing or validating the content retrieved from the browser before the agent processes or interacts with it.

form-testing