Agent Security Needs Redefinition through a Holistic Framework

• URL: http://arxiv.org/abs/2607.22024v1
• Date: Fri, 24 Jul 2026 06:43:09 GMT
• Title: Agent Security Needs Redefinition through a Holistic Framework
• Abstract summary: Defenses ask whether an instruction looks malicious. Benchmarks ask whether an agent performs a harmful sounding action.<n>We operationalize contextual security through four properties that must hold jointly and be evaluated continuously across the agent's trajectory.
• Score: 46.88917910966891
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent security is widely treated as a question about action content. Defenses ask whether an instruction looks malicious. Benchmarks ask whether an agent performs a harmful sounding action. \textbf{We argue that agent security is fundamentally a contextual problem, and that the current content based framing systematically misdefines it.} A command to ``delete user data'' might be a routine administrative request or a prompt injection attacking production systems, and the content alone cannot distinguish the two. Authorization context can. Across every injection task in AgentDojo and WASP, the same action is one an authenticated user would plausibly request in a routine workflow, which makes the conflation a structural property of evaluating security through content. We operationalize contextual security through four properties that must hold jointly and be evaluated continuously across the agent's trajectory. Source Authorization asks who issued the command. Task Alignment specifies the agent's authorized objective. Action Alignment evaluates whether each action serves that objective. Data Isolation governs information flows across privilege boundaries. Under this reframing, indirect prompt injection becomes a Source Authorization violation. Snapshot benchmarks are structurally incapable of evaluating Data Isolation. Existing defenses are reorganized around the property they actually approximate. The contextual reframing changes which defenses are coherent, which evaluations measure something useful, and which attack patterns evaluation can see at all.

Related papers

• ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents [11.495797074855703]
  We propose ActGuard, a pre-execution action auditing framework.<n>Rather than judging whether external content is inherently suspicious, ActGuard assesses whether it causes the current action to deviate from a reasonable expectation.<n>A verifier then examines the localized evidence, masks only spans confirmed as malicious, and regenerates the action from the sanitized context.
  arXiv  Detail & Related papers  (2026-09-14T03:47:05Z)
• ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection [61.4148196085256]
  We present ROPE (Routed Origin Policy Enforcement), which is anchored in a structural notion of trust.<n>Our approach admits two provable guarantees: 1) at every step of a trajectory, no value whose only origin is attacker-writable content reaches an origin-guarded parameter, and 2) no rewording of an injection changes an admission decision.
  arXiv  Detail & Related papers  (2026-08-27T01:22:14Z)
• SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response [38.89333299127352]
  We introduce SecRespond, the first benchmark for evaluating Large Language Model (LLM) agents on the post-compromise incident-response workflow.<n>We instantiate this task across 10 cyber ranges, each constructed from a distinct compromised cloud host.<n> Experimental results show that although current agents can reliably uncover the problems exposed by alerts, they struggle to proactively investigate the disk for silent intrusions.
  arXiv  Detail & Related papers  (2026-07-29T11:32:23Z)
• Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response [0.0]
  Cyber-capable AI agents combine language models with tools, memory, and execution environments to perform offensive-security tasks.<n>This review synthesizes five vulnerability classes at that boundary: multi-step offensive chains, objectives that conflict with sandbox boundaries, supply-chain and credential exposure, persistent command-and-control, and the speed of automated action.
  arXiv  Detail & Related papers  (2026-07-28T07:34:37Z)
• AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents [57.34566159148893]
  Indirect prompt injection (IPI) is a major security threat to LLM-powered agents.<n>We develop AutoDojo, an adaptive extension of AgentDojo that optimize IPI against a given defense.
  arXiv  Detail & Related papers  (2026-06-13T02:09:08Z)
• Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents [93.19140872946842]
  Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments.<n>This makes them vulnerable to prompt-injection attacks, in which seemingly benign content embeds adversarial instructions that manipulate agent behaviour.<n>We introduce textbfsysname, a benchmark to systematically categorize and attribute harm in real-world web agent systems.
  arXiv  Detail & Related papers  (2026-06-11T14:12:43Z)
• Aligning Provenance with Authorization: A Dual-Graph Defense for LLM Agents [11.867868278947524]
  LLM-based agents are increasingly deployed in high-stakes scenarios such as email management, financial transactions, and code execution.<n>We propose AuthGraph, a dual-graph alignment defense framework that constructs two complementary graphs.<n>On AgentDojo, AuthGraph reduces the attack success rate from 40% to 1% while maintaining 76% task completion rate on GPT-4o; on AgentDyn, it reduces the attack success rate from 39% to 2% while preserving 51% utility.
  arXiv  Detail & Related papers  (2026-05-26T03:20:23Z)
• AgentSecBench: Measuring Prompt Injection, Privacy Leakage, and Tool-Use Integrity in LLM Agents [0.2864713389096699]
  We introduce AgentSecBench as an empirical instantiation of a formal security framework for this problem.<n>It defines three games-instruction-integrity, retrieval-confidentiality, and capability-integrity-under a common notion of intent-to-execution noninterference with permitted leakage.<n>It represents an application policy as a projection onto authorized observations and capabilities, distinguishes prompt annotations from enforcing projections, and measures both adversarial advantage and whether a defense closes the relevant model-visible channel before generation.
  arXiv  Detail & Related papers  (2026-05-25T18:53:22Z)
• Securing LLM Agents Need Intent-to-Execution Integrity [49.490963596514185]
  We argue that securing LLM agents requires defining an end-to-end correctness property that specifies when an agent's execution faithfully reflects the user's intent.<n>We observe that LLM agents are structurally analogous to compilers, where security violations correspond to mis-executions that do not preserve user intent.<n>We derive four integrity properties that must hold simultaneously: emphTool Integrity, emphInstruction Integrity, emphJudgment Integrity, and emphData Flow Integrity.
  arXiv  Detail & Related papers  (2026-05-16T12:53:31Z)
• Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw [9.193028511327851]
  This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in OpenClaw.<n>DeepTrap balances risk realization, benign-task preservation, and stealth.<n>Results show that contextual compromise can induce substantial unsafe behavior while preserving user-facing task completion.
  arXiv  Detail & Related papers  (2026-05-11T13:20:02Z)
• ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection [28.414099578635373]
  We present AgentLure, a benchmark that captures context-dependent tasks and context-aware prompt injection attacks.<n>To address this limitation, we propose ARGUS, a defense mechanism that enforces provenance-aware decision auditing for LLM agents.
  arXiv  Detail & Related papers  (2026-05-05T05:37:00Z)
• A Framework for Formalizing LLM Agent Security [46.86073273904095]
  Security in LLM agents is inherently contextual.<n>Existing definitions of security attacks against LLM agents often fail to capture this contextual nature.<n>We present a framework that systematizes existing attacks and defenses from the perspective of contextual security.
  arXiv  Detail & Related papers  (2026-03-19T21:01:49Z)
• Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
  We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
  arXiv  Detail & Related papers  (2024-06-18T17:32:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.