Wardstone is an LLM security API that acts as a firewall between your application and any LLM provider. It detects prompt injections, jailbreaks, harmful content, data leakage, and suspicious links in a single API call with sub-30ms latency. Scan both user inputs and model outputs for threats. One endpoint returns risk bands across four detection categories: prompt attacks, content violations, data leakage (PII like SSNs, credit cards, emails), and unknown links. Drop-in REST API with official SDKs for TypeScript, Python, Go, Ruby, PHP, Java, and C#. Works with any LLM provider including OpenAI, Anthropic, Google, Meta, and Mistral. Free tier with 10,000 API calls/month, no credit card required.