CVE-2026-108600 open-multi-agent 1.5.0 through 1.21.2 Sandbox Escape via file_write Dangling Symlink

open-multi-agent @open-multi-agent/core 1.5.0 through 1.21.2 contains a link following vulnerability in the filewrite tool sandbox that allows attackers to create files outside the workspace root by using dangling symlinks. Attackers can plant a dangling symlink in the workspace and steer the age...

CVE-2026-108600 open-multi-agent 1.5.0 through 1.21.2 Sandbox Escape via file_write Dangling Symlink

open-multi-agent @open-multi-agent/core 1.5.0 through 1.21.2 contains a link following vulnerability in the filewrite tool sandbox that allows attackers to create files outside the workspace root by using dangling symlinks. Attackers can plant a dangling symlink in the workspace and steer the age...

EUVD-2026-96392

open-multi-agent @open-multi-agent/core 1.5.0 through 1.21.2 contains a link following vulnerability in the filewrite tool sandbox that allows attackers to create files outside the workspace root by using dangling symlinks. Attackers can plant a dangling symlink in the workspace and steer the age...

CVE-2026-108600

The open-multi-agent (@open-multi-agent/core) package (versions 1.5.0 through 1.21.2 ) is vulnerable to a link following vulnerability (CWE-59) within the file_write tool sandbox . This flaw allows an attacker to escape the workspace root and create files in unauthorized locations by using dangli...

CVE-2026-108600: Improper Link Resolution Before File Access

open-multi-agent @open-multi-agent/core 1.5.0 through 1.21.2 contains a link following vulnerability in the filewrite tool sandbox that allows attackers to create files outside the workspace root by using dangling symlinks. Attackers can plant a dangling symlink in the workspace and steer the age...

Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security

LLM-based multi-agent systems MAS engage tools, share memory, and delegate tasks, often encountering adversarial content. Current defenses for MAS are typically evaluated in isolation, focusing on one attack type at a time, which can lead to costly and hard-to-audit outcomes. This study organizes...

Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement

Agentic AI is emerging as a promising paradigm for automating complex cybersecurity decisions, yet its use in enforcing zero trust introduces significant challenges in safety, reliability, and policy compliance. This paper presents Agentic AI based zero trust architecture Agentic-ZTA that...

Can CaMeLs Talk? Securing Multi-Agent Systems against Indirect Prompt Injection Attacks

Indirect prompt injection attacks - malicious instructions embedded in content processed by large language models - remain a major obstacle to safely deploying tool-using agents. CaMeL Debenedetti et al., 2025 mitigates this threat for an individual agent by separating trusted control flow from...

MIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication

Inter-agent communication is central to Large Language Model Multi-Agent Systems LLM-MAS, but it introduces an underexplored vulnerability: Agent-in-the-Middle AiTM attacks that manipulate messages in transit without compromising the agents themselves. Prior work reports Attack Success Rates ASR...

MADBench: Benchmarking the Security of Multi-Agent Debate

Multi-agent debate MAD can improve large language model LLM reasoning by allowing multiple agents to exchange and critique their answers to the same task. However, the interactions that enable agents to correct mistakes can also spread adversarial errors and steer the agents toward an incorrect...

Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems

As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has examined this risk primarily in adversarial settings, where agents are instructed or rewarded to communicate covertly and evade oversight. We show th...

Speculative Safety Honeypot: Toward Proactive Defense against Multi-Turn Agent Attacks

As Large Language Model LLM agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant security challenge. Existing detection methods typically rely on historical context. However, this retrospective logic struggles to identify deep maliciou...

One Pipeline Does Not Fit All: TAILOR, a Type- and State-Aware Framework for CVE Reproduction

Growing vulnerability disclosure and widespread software reuse increase security teams' need for reproducible evidence to diagnose vulnerabilities, validate patches, and build regression tests. Producing such evidence at scale requires automated end-to-end CVE reproduction. Existing methods...

Concealing LLM-Based Multi-Agent Topology Via Phantom Structure Injection

Driven by the rapid advancement of large language models LLMs, LLM-based multi-agent systems MAS have emerged as a powerful paradigm for collaborative reasoning over complex tasks. A key design element of MAS is the communication topology, which governs information flow among agents and often...

DGF-Bench: A Benchmark for Simulating and Auditing Deception against Multi-Agent Governance Boards

Tool-using language-model agents can review enterprise projects as governance boards do: they read the evidence, apply written rules and decide whether the project may proceed. Part of that evidence comes from suppliers and project members with a stake in the decision. DGF-Bench is a benchmark in...

Tracekit: Tamper-Evident Intent-Reasoning-Action Auditing for Autonomous Coding Agents

Autonomous coding agents read untrusted files, run shell commands and spawn sub-agents with little supervision, yet their record is usually an editable log. We present Tracekit, an open-source, dependency-free system that captures three channels for every agent session: what the human asked inten...

AI-Based Vulnerability Assessment Capability and Cyber Attack Graph Analysis

Cyber threats targeting mission-critical infrastructure are becoming more sophisticated while the barrier to launching attacks continues to fall. Traditional point solutions like antivirus and firewalls are reactive and fail to address the combinatorial complexity of modern attack surfaces. This...

ORBIT: A Framework for Multi-Agent Safety and Security Evaluations

Multi-agent LLM systems are increasingly deployed for complex, long-horizon tasks or emerge as a natural consequence of agents interacting in the wild. Yet they give rise to significant safety and security risks: the flexible protocols that enable task generalization also expose novel threats, fr...

Agent Name Collision Attacks in Multi-Agent Systems

Multi-agent hosts turn remote Agent Cards into local agents, tools, workflow targets, and broker routes. A2A defines the card's name as human-readable metadata, not as a stable identity, and specifies no collision semantics. The security failure begins when a host nevertheless uses that remote na...

Blockchain-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity Applications

Blockchain and artificial intelligence AI are converging into a single infrastructural layer for securing data sharing, model integrity, and autonomous decision-making across distributed systems. This paper presents a meta-synthesis that draws together four constituent studies covering adversaria...