The paper examines the security challenges of delegating authority to autonomous LLM agents that act on users’ behalf. It introduces a threat model with four adversaries and eight security requirements, demonstrates that current frameworks (LangGraph, CrewAI, AutoGen, MCP) fail to meet these standards, and presents an authorization broker that blocks all identified threats with minimal overhead. The broker is shown to resist numerous attacks and limits compromised sub‑agents to their delegated tasks, and its principles are implemented in VotalAI’s LLM Shield.
By Panduranga Sai Varma Dantuluri, Jyotirmoy Sundi
ActGov is a runtime enforcement framework that validates each action proposed by a large language model (LLM) agent before it interacts with external tools, ensuring that actions stay within task‑scoped authorization boundaries and comply with dynamically constructed policies. It builds policies from tool specifications, benign tasks, and failure traces, verifying updates via SMT‑based counterexample checking. In evaluations on AgentDojo and AgentDyn benchmarks, ActGov consistently reduces indirect prompt‑injection attack success while maintaining task utility, outperforming existing defenses.
By Kaiyuan Zhang, Yuke Peng, Ke Jiang, Yinqian Zhang
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.
By Yuchen Ling, Shengcheng Yu, Zhenyu Chen, Chunrong Fang
The paper introduces BSC‑R, a deterministic effect‑boundary mechanism that ties a single‑use commit authorization to the specific action and the semantic state that justified it, aiming to close the proposal‑to‑commit gap in tool‑using language‑model agents. Experiments on 2,847 AgentDojo episodes and 10,302 frozen proposals show that BSC‑R preserves the agent’s original behavior while rejecting unauthorized changes, and further tests on a boundary‑drift experiment and the CONTINUITY suite demonstrate high success rates in valid contexts and robust handling of replay and ambiguous cases. However, broader testing reveals that BSC‑R still allows a 25% invalid‑effect commit rate in a larger attack set, indicating that it provides scoped, not universal, safety.
By Wesley Shu
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...
By Rui Yang, Junjie Xu, Zhengyu Liu, Neil Fendley, Yang Hong, Ziyang Li, Yinzhi Cao
arXiv:2607. 10487v1 Announce Type: cross Abstract: LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a DOM snapshot, approval epoch, version witness, branch token, or worker result.
By Igor Santos-Grueiro
arXiv:2606. 09549v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any final output check can intervene.
By Yuhan Ma, Stefan Schmid
arXiv:2608.29381v1 Announce Type: cross
Abstract: AI agents are moving toward persistent, stateful execution across various applications, accumulating execution state and external effects that are co...
By Guanlong Wu, Dahui Li, Ke Jiang, Jianyu Niu, Cong Wang, Yinqian Zhang
arXiv:2606. 11632v1 Announce Type: cross Abstract: Agentic infrastructure introduces a critical control-plane authorization problem: non-deterministic reasoning systems can propose high-stakes mutations to production resources, yet existing security mechanisms -- such as identity and access management (IAM), policy engines, consensus protocols, and audit logs -- either enforce static, context-unaware permissions or merely record actions post-execution.
By Jun He, Deying Yu
Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subsequent actions and exceed user authorization. Existing...
The paper introduces PACE, a Provenance-Aware Capability Enforcement system designed to secure tool-using large language model agents by mediating every tool call before execution. PACE employs path confinement to limit influence paths and verifies effects against authenticated authority, distinguishing certified execution contracts from evaluated configurations. Experiments on eight agent‑security benchmarks show that the evaluated configuration reduces attack success in most cases while maintaining near‑native utility.
By Fengpeng Li, Qizhou Wang, Yuke Hu, Kemou Li, Jun Liu, Haiwei Wu, Jiantao Zhou, Di Wang
arXiv:2607. 24625v1 Announce Type: cross Abstract: Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors.
By Arseny Kravchenko, Vadim Liventsev, Innokentii Konstantinov, Ildar Iskhakov, Matvey Kukuy