Bounded Agents: Delegation Security for Multi-Agent AI Systems

• URL: http://arxiv.org/abs/2608.15888v1
• Date: Sun, 16 Aug 2026 18:38:00 GMT
• Title: Bounded Agents: Delegation Security for Multi-Agent AI Systems
• Abstract summary: LLM-based agents can act on behalf of a user to access cloud services, call tools, or invoke agents.<n>At session start, the agent's permissions are set but remain static, and each request is evaluated independently.<n>A prompt injection poses a risk only if the agent has authority to perform such actions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-based agents can act on behalf of a user to access cloud services, call tools, or invoke agents. At session start, the agent's permissions are set but remain static, and each request is evaluated independently, without considering prior actions. Within its permissions, an agent may act contrary to the delegated task, combine individually permitted actions into a prohibited outcome, or delegate authority to a sub-agent without limiting it. A prompt injection poses a risk only if the agent has authority to perform such actions; this is therefore a problem of authorization architecture, not just the model. The Agentic Principal Chain (APC) tracks delegated authority from one principal to the next. APC evaluates each request against the accumulated session state using six authorization checks. APC carries forward and restricts delegated scope and budgets. Using composition closure, APC checks requests against prior actions to prevent prohibited combinations and enforces the decision outside the model. We prove Blast Radius Monotonicity and Composition Soundness for APC implementations; Composition Soundness is limited to prohibited combinations under a complete restriction set and serialized admission. We evaluated 3,154 instances including InjecAgent, AgentDojo, and ASB. Our compromised-model evaluation tests APC independently of model behavior by inserting the ground-truth attack call after the first legitimate tool call. AgentDojo exfiltration fell from 75-100% to 0% across all four domains; APC blocked all 544 InjecAgent data-stealing cases. Intent binding reduced destruction from 38.6% to 4.0% and manipulation from 90.5% to 12.1%. Authorization latency was 0.24 ms at the 99th percentile on an idle host; across 949 AgentDojo task-injection pairs, utility was 8.6 and 13.9 percentage points lower in the two settings. Implementation, evaluation tools, and data are publicly available.

Related papers

• Delegation Without Trust: An Empirical Gap Analysis of Identity, Authorization, and Runtime Governance in Multi-Agent LLM Systems [0.0]
  We present a threat model for multi-agent delegation centered on four adversaries.<n>We show a default runtime modeling common practice fails all four threats.<n>We implement and adversarially evaluate an authorization broker that closes the gap.
  arXiv  Detail & Related papers  (2026-08-31T19:09:34Z)
• ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents [24.540638169054812]
  A single agent hijacked by a malicious third-party skill can cause data exfiltration, privilege escalation, or cascading compromise.<n>We present ClawSentry, an open-source, framework-agnostic security supervision gateway for agent runtimes.
  arXiv  Detail & Related papers  (2026-08-21T13:47:51Z)
• aiAuthZ: Off-Host, Identity-Bound Authorization for AI Agents [0.0]
  I present aiAuthZ, an authorization gateway that moves the safety decision off the agent's host.<n>Every decision joins a SHA-256 hash-chained audit log, and each accepted message yields an HMAC-authenticated QR receipt.<n> residual attack success falls to 0% for all 15 models at no more than 0.03 ms of added decision latency.
  arXiv  Detail & Related papers  (2026-07-06T18:00:49Z)
• Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens [65.53494487819053]
  Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services.<n>We adopt a computer-system analogy: treating a Claw-like agent as an agentic computer system whose gateway runtime plays an OS-like mediation role.<n>We develop SafeClawArena, a benchmark of 406 adversarial tasks across four attack surfaces.
  arXiv  Detail & Related papers  (2026-06-29T18:00:45Z)
• Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? [54.701199583505144]
  Cross-application access creates a privacy risk that has been largely overlooked.<n>We introduce AgentCIBench, an evaluation harness that turns this risk into executable, deterministically scored scenarios.<n>We evaluate 15 frontier agents and find a surprisingly high failure rate.
  arXiv  Detail & Related papers  (2026-06-22T11:36:58Z)
• Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control [0.0]
  Large language models increasingly operate as autonomous agents that select and invoke tools from large registries.<n>We propose a governed MCP proxy that enforces attribute-based access control (ABAC) at two points: tool discovery and tool invocation.<n>Our proxy reduces unauthorized invocation rate (UIR) to 0% while adding under 50ms median latency.
  arXiv  Detail & Related papers  (2026-05-18T13:52:24Z)
• HiveMind: OS-Inspired Scheduling for Concurrent LLM Agent Workloads [0.0]
  In a motivating incident, 3 of 11 parallel agents died from connection resets and HTTP 502 errors - a 27% failure rate.<n>We present HIVEMIND, a transparent HTTP proxy that applies five OS-inspired scheduling primitives to eliminate the failure modes caused by uncoordinated parallel execution.
  arXiv  Detail & Related papers  (2026-04-18T18:59:33Z)
• Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents [0.0]
  Open Agent Passport (OAP) is an open specification and reference implementation that intercepts tool calls synchronously before execution.<n>OAP enforces authorization decisions in a measured median of 53 ms (N=1,000)<n>The same infrastructure that enforces security constraints also enforces quality gates, operational contracts, and compliance controls.
  arXiv  Detail & Related papers  (2026-03-21T21:34:09Z)
• Agent Control Protocol: Admission Control for Agent Actions [0.4929694290403903]
  Agent Control Protocol (ACP) is a formal specification for admission control governance of autonomous agents in B2B institutional environments.<n>ACP defines cryptographic identity, capability-based authorization, deterministic risk evaluation, chained delegation, and cryptographically-chained auditing.<n>ACP operates on top of RBAC and Zero Trust, addressing what neither model solves.
  arXiv  Detail & Related papers  (2026-03-19T12:28:28Z)
• CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution [49.689452243966315]
  AI agents equipped with tool-calling capabilities are susceptible to Indirect Prompt Injection (IPI) attacks.<n>We propose CausalArmor, a selective defense framework that computes lightweight, leave-one-out attributions at privileged decision points.<n> Experiments on AgentDojo and DoomArena demonstrate that CausalArmor matches the security of aggressive defenses.
  arXiv  Detail & Related papers  (2026-02-08T11:34:08Z)
• Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition [101.86739402748995]
  We run the largest public red-teaming competition to date, targeting 22 frontier AI agents across 44 realistic deployment scenarios.<n>We build the Agent Red Teaming benchmark and evaluate it across 19 state-of-the-art models.<n>Our findings highlight critical and persistent vulnerabilities in today's AI agents.
  arXiv  Detail & Related papers  (2025-07-28T05:13:04Z)
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• Malicious Agent Detection for Robust Multi-Agent Collaborative Perception [52.261231738242266]
  Multi-agent collaborative (MAC) perception is more vulnerable to adversarial attacks than single-agent perception. We propose Malicious Agent Detection (MADE), a reactive defense specific to MAC perception. We conduct comprehensive evaluations on a benchmark 3D dataset V2X-sim and a real-road dataset DAIR-V2X.
  arXiv  Detail & Related papers  (2023-10-18T11:36:42Z)

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.