Novee has introduced AI Red Teaming for LLM Applications as part of its AI penetration testing platform. The new capability uses an autonomous AI agent to simulate sophisticated real-world attacks on LLM-powered applications, helping security teams identify vulnerabilities such as prompt injection, jailbreaks, data exfiltration, and agent manipulation before they can be exploited.
Enterprises are rapidly deploying AI-enabled applications ranging from customer-facing chatbots to internal copilots and autonomous agents. These systems introduce a new attack surface that traditional pentesting tools, built for web and infrastructure testing, are not equipped to handle. Novee’s AI pentesting agent addresses this gap by continuously probing applications with adversarial techniques that mirror how real attackers operate.
The AI agent autonomously chains attack techniques together to test how LLM-powered applications behave under pressure. It evaluates responses to sophisticated inputs and produces detailed vulnerability reports with clear remediation steps, enabling security teams to strengthen defenses proactively.
Novee’s research team, drawing from extensive offensive security experience, continuously feeds new findings into the agent. Recent research includes a vulnerability affecting Cursor that enabled remote code execution through context window manipulation, with additional responsible disclosures underway. This ongoing research ensures the agent remains effective against emerging AI-specific threats.
“I've spent twenty years on the offensive side of cyber, inside government operations, protecting critical infrastructure, and now building AI systems that think like real attackers,” said Ido Geffen, CEO and co-founder of Novee. “What we see consistently is that attackers compress timelines dramatically. The window between vulnerability and exploitation can shrink to minutes. Defending against that requires continuous testing, not periodic assessments.”
“AI applications introduce an entirely new attack surface, but most organizations are still testing them with tools designed for web applications and infrastructure,” said Gon Chalamish, co-founder and CPO of Novee. “Attackers are already adapting their techniques for AI systems. Security teams need a way to test those systems the same way adversaries attack them.”
The solution works across any LLM-powered application regardless of the underlying model provider or architecture and can be integrated into existing security workflows and CI/CD pipelines.
About Novee
Novee is the AI penetration testing platform built to secure constantly changing environments against attackers operating at machine speed. Its purpose-trained AI reasons like a real attacker, uncovers novel attack paths continuously, and delivers precise, personalized fixes so teams can stay one step ahead of hackers. Founded by national-level offensive security leaders Ido Geffen, Gon Chalamish, and Omer Ninburg, Novee has raised $51.5 million within four months of its inception from leading investors including YL Ventures, Canaan Partners, and Zeev Ventures.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.