The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns such as prompt injection, obfuscation, or data exfiltration attempts were detected across the provided resources.
[EXTERNAL_DOWNLOADS] (SAFE): The skill references standard, reputable development dependencies (e.g., MUI, TanStack, Zod). These are cited within the context of architectural guidance rather than as scripts to be executed or downloaded by the agent itself.
[DATA_EXPOSURE] (SAFE): Authentication patterns demonstrate the use of a dedicated useAuth hook and avoid hardcoded credentials or insecure data storage practices.
[COMMAND_EXECUTION] (SAFE): No shell commands, system calls, or dangerous subprocess executions were found; all code examples are strictly frontend UI or state management logic.
[PROMPT_INJECTION] (SAFE): Technical instructions are purely focused on code quality and architectural standards without any attempts to bypass safety filters or override agent behavior.

frontend-dev-guidelines