The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill utilizes external data which establishes an attack surface for indirect prompt injection.
Ingestion points: The skill accepts untrusted parameters including url (dev server URL) and selector (CSS selector) in SKILL.md under the 'Receive Fix Context' step.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the ingested content are present.
Capability inventory: The skill possesses browser automation capabilities through Playwright, enabling it to navigate to provided URLs and interact with page elements.
Sanitization: There are no instructions provided for the validation or sanitization of input URLs or selectors before they are used in automation tasks.

playwright-verifier