Agentic Security is an open-source vulnerability scanner for LLM agent workflows that tests AI systems against jailbreaks, fuzzing, and multimodal attacks. It probes weaknesses across text, image, and audio inputs through multi-step jailbreak simulations, randomized stress testing, and reinforcement learning-powered adaptive attacks. The toolkit connects directly to LLM APIs for high-volume real-world attack scenarios, helping developers identify and patch safety gaps before deployment.
Agentic Security is a 100% free and open-source AI vulnerability scanner and red-teaming tool under the Apache-2.0 license. It provides customizable datasets and automated prompt-fuzzing algorithms to detect prompt injections, jailbreaks, and SSRF vulnerabilities in LLMs with no software costs.
