Recon runs automated and comprehensive penetration testing attacks on your LLM powered applications, to help protect you from unique security threats and vulnerabilities. It has the ability to run attacks from an attack library, use an agent for completely automated scans or perform human augmented scans using an LLM Agent.
ModelScan is an open source project from Protect AI that scans models to determine if they contain unsafe code.
CyberSecEval is an extensive benchmark suite under Meta PurpleLlama, designed to evaluate various cybersecurity risks of LLMs, including several listed in the OWASP Top-10 for LLMs.
Cisco AI Validation assesses AI applications and models for security and safety vulnerabilities. We automatically analyze a model’s risk across hundreds of attack techniques and threat categories so you can defend against them.
Cisco AI Validation Read Post »
Enkrypt AI secures enterprises against generative AI risks with its comprehensive security platform that detects threats, removes vulnerabilities, and monitors the latest insights on security, compliance and AI performance.
Aqua facilitates secure application development and runtime protection by addressing vulnerabilities outlined in the OWASP Top 10 for LLM applications.
Prompt Fuzzer is an interactive, open-source tool that empowers developers of GenAI applications to evaluate and enhance the resilience and safety of their system prompts. The users input any system prompt and the relevant configuration, and the Fuzzer starts running its tests.
Pillar enables teams to rapidly adopt AI with minimal risk by providing a unified AI security layer across the organization
ZenGuard AI offers a dev-first API platform for the fastest low-latency GenAI guardrails and hassle-free vulnerability testing for AI applications.
warranty of service or accuracy. For more information, please refer to our General Disclaimer. – Copyright © 2025 OWASP Foundation, Inc.