PromptBrake

什么是 PromptBrake？

PromptBrake helps teams security-test LLM-powered API endpoints with a fixed suite of 60+ attack scenarios. Connect your endpoint, run scans, and review PASS/WARN/FAIL results with evidence and remediation guidance. It covers prompt injection, prompt leaks, data exposure, tool abuse, and output bypasses across OpenAI, Claude, Gemini, and many custom LLM-backed APIs. API keys are not stored, and PromptBrake analyzes results without sending your scan data to another LLM.