This paper conducts the first real-world safety evaluation of the personal AI agent OpenClaw, demonstrating that its broad system access creates inherent vulnerabilities that significantly increase th…

The paper introduces SkillVetBench, a novel two-stage benchmark that effectively detects and verifies malicious behavior in open agentic skill ecosystems, significantly outperforming existing static a…

The paper introduces SkillVetBench, a novel two-stage benchmark that effectively detects and verifies malicious behavior hidden within open agentic skills, significantly outperforming static and seman…

The paper proposes extbackslash codeName, a behavioral firewall that uses a parameterized deterministic finite automaton (pDFA) to enforce verified benign tool-call sequences and parameter bounds for…

The paper introduces LoopTrap, an automated red-teaming framework that demonstrates how malicious prompts can poison the termination judgment of LLM agents, causing unbounded computation.

The paper introduces SkillSafetyBench, a comprehensive benchmark demonstrating that agent safety failures often stem from adversarial influences within reusable skills and execution environments, rath…

The paper proposes SafeClaw-R, a novel framework that enforces safety as a system-level invariant over the execution graph to mitigate the high safety and security risks inherent in autonomous multi-a…

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…

The paper introduces Behavioral Integrity Verification (BIV), a framework that systematically audits AI agent skills by comparing their declared capabilities against their actual implementation, revea…

This paper identifies and characterizes 'guidance injection,' a stealthy attack vector that embeds adversarial operational narratives into autonomous coding agents' bootstrap guidance, demonstrating h…

The paper argues that the Authorization-Execution Gap (AEG)—the divergence between intended authorization and actual execution—is a critical safety and security flaw in open-world agents, requiring so…

ClawKeeper is a comprehensive, multi-layered security framework designed to mitigate critical vulnerabilities in autonomous agent runtimes like OpenClaw by enforcing protection across skills, plugins,…

The paper introduces Owner-Harm, a formal threat model addressing the critical blind spot of AI agents harming their own deployers, demonstrating that specialized defenses are needed beyond generic sa…

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 investigates the forensic analysis of agentic AI systems using OpenClaw, proposing an agent artifact taxonomy and highlighting the challenges posed by non-determinism in agent-mediated exec…

The paper demonstrates that current agentic-AI runtimes are fundamentally insecure and architecturally obsolete because they fail to detect critical safety failures, proposing a superior, hardened alt…

The paper introduces TraceSafe-Bench, a comprehensive benchmark, and finds that securing LLM agents requires jointly optimizing for structural reasoning and safety alignment to mitigate risks during m…

The paper introduces DeepTrap, an automated framework that evaluates security vulnerabilities in agentic language models by manipulating their internal execution contexts, demonstrating that task comp…

The paper introduces AgentSecBench, a security evaluation framework that measures prompt injection, privacy leakage, and tool-use integrity in LLM agents by defining formal security games and testing…

The paper introduces MonitoringBench, a semi-automated red-teaming methodology that generates diverse and stronger attacks, revealing that current coding-agent monitors often fail against sophisticate…