ZeroLeaks
Shield SDKProvider Wrappers

Provider Wrappers

Drop-in wrappers for OpenAI, Anthropic, Groq, and Vercel AI SDK. Auto-harden, detect, and sanitize.

Provider Wrappers

Shield provides wrappers for popular LLM clients. Each applies hardening, injection detection, and output sanitization automatically. Default onDetection is "block" (throws on injection).

OpenAI

shieldOpenAI(client, options) wraps chat.completions.create.

Anthropic

shieldAnthropic(client, options) wraps messages.create.

Groq

shieldGroq(client, options) wraps chat.completions.create.

Vercel AI SDK

shieldMiddleware and shieldLanguageModelMiddleware for generateText/streamText.

sanitize()

N-gram matching to detect and redact leaked system prompt fragments in model output.

OpenAI Provider

Wrap your OpenAI client with Shield protection for automatic prompt hardening, injection detection, and output sanitization.

On this page

Provider Wrappers