The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using npx impeccable to run a deterministic design detector on source files and to manage a local 'live' server for browser-based detection.
[REMOTE_CODE_EXECUTION]: It dynamically injects a script into the browser context from a locally hosted server (http://localhost:PORT/detect.js) to highlight design issues via overlays.
[EXTERNAL_DOWNLOADS]: The use of npx may trigger the download of the impeccable package from the npm registry if it is not already present in the environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data which creates an attack surface for indirect prompt injection.
Ingestion points: The skill reads source code files (HTML, JSX, TSX, Vue, Svelte) and navigates to live URLs provided by the user.
Boundary markers: There are no explicit instructions or delimiters used to tell the agent to ignore any natural language instructions that might be embedded within the analyzed files or web pages.
Capability inventory: The agent has the ability to execute shell commands, run arbitrary Javascript in a browser, and spawn sub-agents, which could be abused if an injection is successful.
Sanitization: The skill does not perform any sanitization or validation of the content it reads before processing it.

i-critique