toolgrep

toolgrep / Security

PromptBrake

Automated AI security testing for LLM APIs and chatbots

Visit promptbrake.com →DocsPricing

PromptBrake is an automated security testing platform for LLM-powered API endpoints and AI chatbots. It sends controlled adversarial prompts to staging endpoints, checks for prompt injection, data leakage, unsafe tool behavior, and output bypasses, and supports CI/CD release gates. It can be self-hosted so prompts, credentials, responses, and evidence stay in customer-controlled infrastructure. Free tools include a test case builder, agent tool-call checks, an OWASP LLM test case mapper, prompt injection payload library, and a read-only MCP server.

Category
Security
Pricing
freemium
Free tier
yes
API
yes
MCP server
yes
SDK
no
Open source
no

#llm-security#prompt-injection#ai-testing#ci-cd#release-gates#mcp#self-hosted#chatbot-testing

Listed 2026-10-29 · last verified 2026-10-29 · extracted by @cf/zai-org/glm-5.3-flash · confidence 0.9

API
curl https://toolgrep.com/api/products/promptbrake