Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.39450

ActionGuard: Tool Call Authorization under Poisoned Skills

Jihun Han·Yejin Jang·Byung Il Kwak·Mee Lan Han
View original source ↗Read source document ↗Export metadata ↓

Abstract

LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. However, malicious instructions inserted into an otherwise benign skill can cause a benign user request to trigger dangerous Tool Calls, including data exfiltration, file deletion, or unauthorized code execution. This paper presents ActionGuard, which inspects skill-influenced Tool Calls immediately before execution. ActionGuard separates the target agent's action-generation context from the safeguard's authorization context. The target agent may use the original skill for planning, but the Reviewer does not receive the potentially poisoned raw skill text. Instead, it determines whether each action is justified by the trusted user request using a balanced skill profile, current and recent Tool Calls, and local script contents. ActionGuard intercepts each Tool Call at OpenClaw's before-tool-call stage and enforces the Reviewer's ALLOW or DENY decision under a fail-closed policy. We evaluate ActionGuard on 139 contextual and 180 obvious injections in a SKILL-INJECT-based setting against Dynamic Guardian and SkillGuard, using three open-source and two commercial Reviewer models. Each condition is repeated three times and evaluated using Attack Success Rate (ASR) and Task Success Rate (TSR). Overall, ActionGuard reduced ASR by 35.54 to 46.11 percent relative to existing safeguards and by 70.44 percent relative to No Safeguard, while maintaining high benign-task completion. These results show that execution-boundary authorization grounded in trusted user intent and runtime evidence can restrict unauthorized Tool Calls induced by skill injection.

Explore related subjects

cs.CRcs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Jihun Han, Yejin Jang, Byung Il Kwak, Mee Lan Han. 2026-09-30. ActionGuard: Tool Call Authorization under Poisoned Skills. https://arxiv.org/abs/2609.39450

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Mitigating Data Reconstruction Attacks in Federated Learning: Conditions, Bounds, and Theoretical Guarantees

Privacy attacks, particularly data reconstruction attacks, pose significant challenges to federated learning despite its promise in privacy-preserving collaborative training. This paper presents a comprehensive theoretical analysis of privacy leakage in federated learning through dual perspectives: linear algebra and optimization theory. By analyzing the client-update Jacobian, we identify conditions under which distinct data batches produce the same model update and derive a sufficient batch-size criterion for non-unique reconstruction. Through optimization theory, we establish a novel upper bound for privacy leakage that incorporates batch size, distortion extent, and other critical parameters. These theoretical insights elucidate the fundamental relationships between system parameters and privacy vulnerability, laying the groundwork for developing more robust privacy-preserving federated learning frameworks.

cs.CR↗
arXiv2026

A Privacy-Preserving Federated Learning Method for Heterogeneous Clients

Federated Learning (FL) with Differential Privacy (DP) can ensure the protection of healthcare data privacy against malicious user attacks. However, FL with the DP method faces an inherent trade-off: stronger privacy protection degrades predictive accuracy due to injected noise. On the other hand, Homomorphic Encryption (HE) enables computations on encrypted data and the aggregation of encrypted gradients without introducing DP-induced noise, thereby potentially increasing the predictive accuracy. However, it may increase the computation cost. To improve the predictive accuracy while considering the computational ability of heterogeneous clients, we propose a Privacy-Preserving Machine Learning (PPML)-Hybrid method. In the proposed PPML-Hybrid method, clients distributedly select either HE or DP based on their computational resources, so that HE clients contribute noise-free updates while DP clients reduce computational overhead. Meanwhile, clients with high computational resources can flexibly adopt HE or DP according to their privacy needs. Performance evaluation on omics datasets shows that our proposed method achieves comparable predictive accuracy while significantly reducing computation time relative to HE-only. Additionally, it outperforms DP-only methods under equivalent or stricter privacy budgets.

cs.CR↗
arXiv2026

Memory-Induced Tool-Drift in LLM Agents

LLM agents increasingly combine long-term memory for personalization with tool calling for taking actions. We study a failure of this combination: personality-driven preferences stored in memory (e.g., cost-consciousness, impatience, risk tolerance) silently shifting tool-call parameters in contexts where they do not apply. We call this memory-induced tool-drift and stress-test it with MEMDRIFT, an iteratively refined benchmark of 105 scenarios spanning five bias dimensions and seven professional domains. Measured as excess parameter degradation over a neutral-memory baseline, biased memories in MEMDRIFT induce drift in all eight models we evaluate, raising degradation rates to 0.38--0.83 versus 0.05--0.12 for neutral memories. The drift persists under three widely used memory frameworks. A vulnerability audit of 6,062 tools across 288 MCP servers demonstrates that real-world tools are also susceptible to this failure mode. Mechanistically, we find that biased memories act as implicit steering vectors along the same direction as explicit behavioral instructions and draw attention away from task-relevant context. Neither prompt-based defenses nor relevance filters offer a complete solution, motivating defenses at the intersection of memory management and tool calling.

cs.CR↗