This paper proposes the Dynamic Security Control Compositor (DSCC), a two-phase approach to compositional security for multi-tool agent chains, preventing unsafe combinations and catching violations a…

The paper argues that agent security must be treated as a systems problem, requiring the enforcement of security invariants at the system level rather than solely relying on improving the underlying A…

The paper systematically evaluates six OpenClaw-series AI agent frameworks, demonstrating that these agentized systems possess significant security vulnerabilities that are distinct from and more seve…

This paper analyzes the security of LLM-based autonomous agents by drawing parallels to operating system security, finding that while some vulnerabilities are inherent, many can be mitigated using est…

AgentGuard is an attribute-based access control framework designed to mitigate severe security risks, such as privacy leakage and system compromise, in tool-using LLM-based agents.

ClawLess introduces a formally verified security framework that enforces fine-grained policies on autonomous AI agents, mitigating risks associated with their ability to run code and retrieve informat…

ChainCaps introduces a novel runtime capability budgeting system that prevents 'permission laundering' in complex tool-using agents, significantly reducing attack success rates while maintaining benig…

The paper introduces AgentWard, a lifecycle-oriented, defense-in-depth architecture designed to systematically secure autonomous AI agents by protecting them across all stages of their operation.

TitanCA presents a novel, multi-agent LLM orchestration framework that significantly improves vulnerability discovery by reducing false positives and identifying numerous zero-day vulnerabilities.

This paper provides the first comprehensive security analysis of the Agent Skills framework, identifying severe structural vulnerabilities that require fundamental architectural changes rather than si…

This paper systematizes the security challenges of open agentic systems, concluding that while attack characterization is mature, the field lacks robust guidelines for operational governance, memory i…

This paper analyzes 470 security advisories in the OpenClaw AI agent framework, demonstrating that the system's structural weakness lies in per-layer trust enforcement, enabling cross-layer remote cod…

This paper provides a systematic, layered review of security risks and defense strategies for autonomous agent frameworks, using OpenClaw as a case study to address the current lack of integrated rese…

The paper introduces Distributed Sentinel, a zero-trust architecture that prevents Context-Fragmented Violations (CFVs) in multi-agent systems by propagating security state across departmental boundar…

The paper develops a unified, cross-layer security framework for autonomous LLM agents operating in agentic commerce, identifying key attack vectors and proposing a layered defense architecture.

The paper reports on penetration tests conducted on proprietary, large-scale AI agent systems, finding that security vulnerabilities persist despite stricter development standards.

This paper proposes a new approach for cryptographically verifiable agent authorization, formalizing it as a relation that binds an agent principal, a request, an execution context, and policy satisfa…

The paper introduces Language-Based Agent Control (LBAC), a new programming model that extends static typing and runtime enforcement guarantees to agentic applications, ensuring that agent-generated c…

This paper systematically maps the expanded attack surface of agentic AI systems, identifying new threat vectors like RAG poisoning and cross-agent manipulation, and proposes a comprehensive security…

The paper introduces Policy-First Tooling, a model-agnostic permission layer that significantly enhances the safety and reliability of tool-orchestrated AI workflows by enforcing explicit constraints…