If you re shipping an AI chatbot or agent and don t know where to start with security testing, I built five free tools in PromptBrake to help.
Get prompt-injection inputs to try, map risks to test ideas, plan release checks, and build response or agent tool-call test packs. No PromptBrake account needed.
You can use them on the web or through MCP in your AI assistant. For example, ask: Help me prepare tests for instructions hidden in documents my chatbot reads. You get test inputs to run against your own app.
Five free tools for AI security test inputs, OWASP risk mapping, release plans, response packs and agent tool-call packs. Use them on the web or through MCP, skills and plugins, with no PromptBrake account or API key. MCP prepares artifacts; it does not run tests. Run tool-call packs with the free GitHub Action using staging dispatcher capture. Response packs need a PromptBrake runner. Captured calls do not prove backend effects or permission enforcement.
