The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of existing Playwright test files to generate documentation. This constitutes an indirect prompt injection surface.
Ingestion points: Reads test_suite and repo_context artifacts as defined in SKILL.md metadata.
Boundary markers: Instructions do not define specific delimiters for separating processed code from agent instructions.
Capability inventory: The skill is explicitly configured with file-writing capabilities (dispatcher-writes-files: true) to update documentation.
Sanitization: No specific validation or sanitization of input code content is performed prior to processing.

playwright-documentation-tests