The Agent Skills Directory

[SAFE]: The skill provides high-quality documentation and code examples for React 18/19, Server Components, and state management without any security risks detected.
[COMMAND_EXECUTION]: No shell commands or dynamic context injections (e.g., !command syntax) are present in the skill files.
[DATA_EXFILTRATION]: While code examples include the use of the fetch API and localStorage, they are used in standard frontend patterns (e.g., data fetching hooks) with placeholder domains like api.example.com. No sensitive data is accessed or exfiltrated.
[REMOTE_CODE_EXECUTION]: The skill references industry-standard packages (e.g., Zustand, Redux, TanStack Query) but does not perform any remote script execution or unverifiable package installations.
[PROMPT_INJECTION]: The instructions are strictly focused on technical implementation and do not contain any attempt to override agent behavior or bypass safety guidelines.

react-expert