ChannelGuard introduces an application‑controlled defense that inspects information at every handoff between models in multi‑agent LLM systems, eliminating the need for extra training or model calls. In over 5,700 test runs across five agent models, it stopped all attacks hidden in tool outputs, and on two open models it reduced successful prompt attacks from 80% to 3% and from 77% to 10%, without affecting accuracy on 30 math problems. The study shows that safety scores can mask very different underlying protections, and that relying solely on model or provider filters may be risky if either changes.
arXiv:2607. 19430v1 Announce Type: cross Abstract: Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can smuggle instructions.
The paper introduces DEFER1, a deterministic-first enforcement system for large‑language‑model based multi‑agent systems that uses 28 checks to block most attacks and refers only a small fraction to human judges. In tests across four domains, DEFER1 reduces attack success from about 30% to roughly 3%, with 78% of attacks blocked deterministically and only a quarter reaching the judges. The study highlights that rules effectively handle clear policy violations while judges address ambiguous intent, but also reveals weaknesses such as a risk‑score gate that misclassifies many proposals.
arXiv:2605.21694v2 Announce Type: replace-cross Abstract: Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender...
arXiv:2609.22949v1 Announce Type: cross Abstract: Existing prompt injection research focuses on single-model chatbot scenarios, where an attacker manipulates one LLM through crafted input. Multi-agen...
MAS-Guard is a unified framework designed to safeguard both single- and multi-agent large language model (LLM) systems. It introduces a local Agent Guardrail (A-Guard) layer that uses task-specific experts to evaluate agentic events, and a system-level Control Plane that applies deterministic structural checks and semantic assessments to routes, capabilities, and message content. The framework enforces interventions—allow, reflection, confirmation, and block—across benchmarks, reducing attack success rates by 71.5‑86.3% while maintaining utility on benign tasks.
arXiv:2609.35807v1 Announce Type: cross Abstract: LLM agents can make unsafe tool calls even when instructed to behave safely. Existing defenses constrain agents before execution, modify tool inputs/...
arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.
arXiv:2606. 02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls.
arXiv:2605. 18414v2 Announce Type: replace-cross Abstract: Large language models increasingly operate as autonomous agents that select and invoke tools from large registries.
arXiv:2607. 10490v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents are attractive for network operations, but tickets, alerts, logs, runbooks, and ChatOps messages can carry indirect prompt injections.
arXiv:2606. 12737v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources.
arXiv:2609.14003v1 Announce Type: cross Abstract: Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provid...