cs.CRMay 17, 2026

Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback

Authors: Lecheng Yan, Ruizhe Li, Xicheng Han, Wenxi Li, Binwu Wang, Longyue Wang, Chenyang Lyu, Guanhua Chen

Organizations: Southern University of Science and Technology · University of Science and Technology of China · Zhejiang University · East China Normal University · Alibaba Group

Abstract

Tool-using LLM agents increasingly rely on external tools to make consequential decisions, yet most existing agent-security benchmarks and defenses implicitly assume that tool feedback is trustworthy once a tool has been selected. We study a different failure mode, cognitive poisoning, in which a malicious tool behaves plausibly during exploration, accumulates trust through benign-looking feedback, and becomes harmful only when hidden state conditions align with the final executable action. To study this setting, we construct TRUST-Bench, a task-conditioned benchmark of 1,970 hidden-trigger tool-compromise episodes with matched safe controls, introduce an asymmetric penalty metric, GuardedJoint, to better reflect real deployment risk, and present VISTA-Guard, a backbone-agnostic framework for final-action risk scoring. The core idea is to abstract multi-step tool interaction into structured environment variables that encode trust-formation dynamics and then score the risk of the final executable action from this trajectory-conditioned representation. Experiments show that prompt-centric heuristics, scalarized features, and zero-shot judges fail in this regime, whereas trajectory-aware final-action scoring yields strong in-domain discrimination and remains effective under balanced out-of-distribution transfer. Under GuardedJoint, VISTA-Guard reaches 84.284.2 in-domain and 56.956.9 on balanced out-of-distribution evaluation, while methods that optimize only one side of the safety--utility tradeoff collapse to zero. These findings support a broader view of agent security in black-box tool ecosystems: the decisive defense target is not local prompt text or tool descriptors alone, but the way trust is formed across the interaction trajectory and committed through the final action.

Explore similar work

CardsList
Jul 23, 2026cs.CR

ToolGuardian: Declarative Security for AI Agent-Tool Interactions

LLM agents increasingly rely on external tools, expanding capability while creating a new security boundary: third-party tools may appear benign at the interface level while embedding unsafe behavior in implementation. Existing defenses rely on weak metadata, collapse characterization and policy judgment into a single decision, or use heuristic/LLM enforcement that lacks deterministic, auditable reasoning over task context and multi-tool composition. This paper presents ToolGuardian, a policy-driven framework for securing agent-tool interactions through pre-admission vetting and task-aware runtime authorization. ToolGuardian uses progressive characterization to convert evidence into structured facts: descriptions capture declared intent, system-call traces expose coarse behavior, mock execution reveals observed effects, and source analysis identifies latent behavior. ToolGuardian's core contribution is an Answer Set Programming (ASP)-based declarative policy layer that reasons explicitly over capabilities, effects, task context, and composition. We compare ASP against heuristic and LLM-based policy realizations using identical inputs and output contracts. We evaluate ToolGuardian on 16 MCP-style tools, including 8 malicious variants derived from real open-source tools, and 20 runtime scenarios. For vetting, ASP reaches a deny-class F1 of 0.86 and 88% accuracy using description, syscall, and observed-effect evidence. For runtime authorization, fully specified realizations classify all scenarios correctly, while ablations show that removing compositional and conformance rules substantially degrades performance.
Arun Ravindran, Saurabh Deochake
Tool-Schema Quality Predicts Tool UseAuthorizationGuardLlm-Based AgentLarge Language Model Safety
AskPDF
Jun 16, 2026cs.CR

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

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. Existing evaluations often collapse these stages into a single attack success rate, making it difficult to tell whether a model merely agreed with an attacker or actually produced observable harm. We introduce SafeClawBench, a staged benchmark for tool-using agent security with 600 controlled adversarial tasks across six attack families: direct and indirect prompt injection, tool-return injection, memory poisoning, memory extraction, and ambiguity-driven unsafe inference. SafeClawBench reports three separate endpoints: semantic attack acceptance, audit-visible harm evidence, and sandbox-observed tool/state harm. Evaluating five agent endpoints under four prompt-level policies, we find that these endpoints capture different failure modes. Without additional prompt protection, semantic failure rates vary widely across models, from 9.0% to 44.2%. Audited harm evidence is narrower than semantic failure, and under a separate executable protocol some matched task identities produce sandbox harm despite passing the Semantic Core call: in a 12,000-row matched analysis, 291 of 347 observed sandbox harms occur in rows that pass the semantic check. Prompt policies change endpoint outcomes, but their effects depend on both model and protocol. SafeClawBench provides a reproducible framework for comparing agent models and prompt-policy conditions without conflating textual compliance, evidence-supported harm, and executable state changes. The open-source dataset is available at https://huggingface.co/datasets/sairights/safeclawbench.
Yuchuan Tian, Mengyu Zheng, Haocheng Mei +5
Large Language Model SafetySecurity AnalysisLlm-Based AgentClawsAgent2AgentAlgorithm Auditing
AskPDF
Jun 9, 2026cs.CR

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

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. This transition changes the nature of security risk. In agentic settings, failures are no longer limited to unsafe text generation. Untrusted content may redirect control flow, misuse tool privileges, corrupt persistent state, leak sensitive information, or trigger harmful external actions. At the same time, research on LLM agent security is expanding quickly but remains fragmented across attack families, defense layers, application domains, and evaluation settings. This paper synthesizes 247 papers through a lifecycle-based, systems-oriented framework that models agent security around the interaction of information flow, delegated authority, and persistent state. We organize the literature around four questions: how LLM agent security should be modeled, which threat surfaces and attack families dominate, what defenses have been proposed and with what tradeoffs, and how security claims are evaluated. We find that prompt injection and tool-mediated control-flow hijacking still dominate the field, while persistent state corruption and multi-agent propagation are becoming central emerging concerns. We further find that current defenses provide useful building blocks but remain weakly compositional, and that existing benchmarks still underrepresent long-horizon, stateful, and deployment-sensitive risks. We argue that secure LLM agents require explicit trust boundaries, principled privilege control, provenance-aware state management, and evaluation practices aligned with realistic operational settings.
Yuchen Ling, Shengcheng Yu, Zhenyu Chen +1
Large Language Model AgentsProduction Agentic SystemsHijackingAdversarial Attack Strategies
AskPDF