Red-Teaming the Agentic Red-Team
For developers and users of agentic red-teaming tools, this work highlights critical security vulnerabilities that could be exploited by adversaries, offering architectural solutions to prevent compromise.
The paper presents the first security analysis of agentic systems for offensive security operations, revealing common design flaws that allow adversaries to exfiltrate API keys, establish persistence, and compromise the operator's machine. The authors propose a robust architecture and design principles to mitigate these attacks.
The use of agentic systems to perform offensive security operations has moved from a theoretical possibility to a commoditized capability. However, while the community has focused on creating more and more capable agents, less attention has been allocated to assessing the security of those systems. In this work, we present the first in-depth security analysis of the most widely used agentic systems for offensive security operations. We show that most of these tools share common design flaws that enable an active adversary to exfiltrate API keys, establish persistent footholds, and fully compromise the operator's machine, even when the agent operates inside a sandboxed container. To support our analysis, we introduce a full cyber kill chain for such agentic systems, capturing the progression from initial LLM manipulation to lateral movement, persistence, guardrail bypass, and sandbox escape. Building on our security analysis, we derive a robust architecture for agentic offensive-security tools and propose actionable, broadly applicable design principles that mitigate the disclosed attack paths at the architectural level.