arXiv AI
Jun 24
Red-Teaming the Agentic Red-Team
arXiv:2606. 24496v1 Announce Type: cross Abstract: The use of agentic systems to perform offensive security operations has moved from a theoretical possibility to a commoditized capability.
Red-Teaming the Agentic Red-Team
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.
Related stories
arXiv AI
Jun 16
A Survey on Agentic Security: Applications, Threats and Defenses
arXiv:2510. 06445v3 Announce Type: replace-cross Abstract: LLM-based agents are now used throughout cybersecurity.
arXiv AI
Jul 21
STAC: When Innocent Tools Form Dangerous Chains for LLM Agents
arXiv:2509. 25624v3 Announce Type: replace-cross Abstract: As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns.
arXiv AI
Jun 2
SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents
arXiv:2606. 02302v1 Announce Type: cross Abstract: Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services.
arXiv AI
Sep 2
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
arXiv:2609.00595v1 Announce Type: cross Abstract: Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating...
arXiv AI
Aug 14
Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents
arXiv:2608. 12977v1 Announce Type: cross Abstract: The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats.
arXiv AI
Jun 10
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
arXiv:2606. 10749v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, and act on external environments.
arXiv AI
Jul 1
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
arXiv AI
Sep 1
AgenTRIM: Tool Risk Mitigation for Agentic AI
arXiv:2601.12449v2 Announce Type: replace-cross Abstract: AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper t...
arXiv AI
Oct 5
Securing Computer-Use Agents Against Branch Steering Attacks
arXiv:2610.03089v1 Announce Type: cross Abstract: Modern Computer Use Agents (CUAs) directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect promp...
arXiv AI
Sep 25
AgentKernel: The Trust-Native Agentic Operating System
AgentKernel proposes a trust‑native operating system for AI agents, arguing that current governance layers are insufficient because they share the same process trust boundary as the agents. The OS introduces a mandatory enforcement boundary organized into four pillars—Identity, Perception, Cognition, and Execution—each adapting classical OS security principles to address semantic‑level failures such as prompt injection, memory poisoning, and tool misuse. By wrapping the agent lifecycle in this structured, non‑bypassable framework, AgentKernel aims to provide a unified security layer that can enforce identity, input mediation, memory governance, and execution control across the entire agent lifecycle.
arXiv AI
Sep 24
Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
The paper introduces ShadowMem, a defensive framework that protects large language model agents from long-horizon threats by maintaining a dedicated safety-focused memory. Inspired by the shadow stack concept, ShadowMem stores safety-critical context throughout an agent’s execution and uses this shadow memory to evaluate the risk of upcoming actions before they are carried out. Experiments show that ShadowMem outperforms existing defenses in detection accuracy, detects most attacks early, and adds minimal overhead to agent performance.