The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-provided source code which represents an indirect prompt injection surface where malicious instructions could be embedded in data.
Ingestion points: User React application source code and configuration files.
Boundary markers: The workflow does not explicitly define delimiters for untrusted user code.
Capability inventory: The skill utilizes npm for building, testing, and linting, and rg for file searching.
Sanitization: No specific sanitization or escaping of user-provided code is mentioned before processing.
[COMMAND_EXECUTION]: Includes instructions for running standard lifecycle scripts such as npm run build, npm run test, and npm run lint within the development environment.
[EXTERNAL_DOWNLOADS]: References and recommends the integration of various well-known third-party libraries and frameworks from trusted ecosystems, including Meta, Microsoft, and the TanStack community.

react