The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill monitors and displays content from external project files, such as Tailwind configurations and CSS files, creating a surface for potential indirect prompt injection if those files contain malicious instructions.
Ingestion points: Reads file content from tailwind.config.*, **/index.css, **/globals.css, **/theme.css, **/Header.*, **/Footer.*, **/App.*, and **/Layout.*.
Boundary markers: The skill uses a 'STOP-SHOW-JUSTIFY' workflow but does not define explicit delimiters to isolate file content from instructions.
Capability inventory: Includes execution of shell commands for visual regression (npx playwright test) and file system operations via Git (git checkout).
Sanitization: No specific sanitization or filtering is applied to the ingested file content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill provides instructions for executing shell commands including git checkout for rolling back design changes and npx playwright test for visual regression testing. These are standard operations for design system management in a software development context.

ui-freeze