Experiments reveal substantial agent vulnerabilities and show that injection timing and placement affect attack effectiveness, and ToolHazard-generated alignment data improves security on both ToolHazard-Bench and AgentDojo while preserving benign task utility.
Abstract
Large language model (LLM) agents integrated with external tools are vulnerable to indirect prompt injections embedded in environmental states. However, existing studies largely rely on manually implemented or reused environments, stochastic LLM-based tool simulation, and predefined injection locations, limiting scalable security research across broader domains. To bridge this gap, we propose **ToolHazard**, a scalable adversarial environment synthesis framework that reduces human engineering and supports expansion with additional seed domains and compute. Through an Environment Simulator, an Attacker Agent, and a User Simulator, ToolHazard synthesizes executable stateful environments, discovers viable injection points and generates environment-specific payloads, and constructs state-grounded long-horizon tasks. Based on ToolHazard, we build **ToolHazard-Bench** for stress-testing agents under complex workflows and diverse environmental attacks. Experiments reveal substantial agent vulnerabilities and show that injection timing and placement affect attack effectiveness. Moreover, ToolHazard-generated alignment data improves security on both ToolHazard-Bench and AgentDojo while preserving benign task utility.
MTGuard is proposed, a hybrid analysis-based defense framework designed to safeguard the use of MCP tools in LLM agents by leveraging lifecycle-aware static-dynamic co-analysis and effectively mitigates multiple categories of harmful tool use across different LLM agents while maintaining performance on benign user tasks.
Ping He, Yuexiang Xie, Yaliang Li et al.· arXiv.org· 0 citations
Agentic systems integrate LLM driven planning with interfaces to external tools, making data leakage and tool misuse feasible via instruction/data boundary failures and prompt injection attacks. Enforcing required controls consistently is particularly challenging in workflows spanning many codebases and heterogeneous agents. To address this challenge in multi agentic systems, we present a pre-deployment pipeline for scanning, hardening, and validation of agentic applications. The pipeline analyzes prompt templates, tool interfaces, and tool-invocation code to identify leakage-enabling patterns and generate actionable patches. The hardened application is then validated through adversarial prompt injection attacks and benign input variations ensuring that mitigations do not disrupt intended behavior. In the hardening stage, high-risk tools are prioritized, and minimally invasive mitigations are applied, including schema tightening, boundary sanitization, allowlist-based tool gating, and least-privilege checks. In the validation stage, the pipeline automatically generates attack inputs that mimic jailbreaks, instruction overrides, and tool-targeted manipulation, along with benign task variants, to confirm that the functionality of the hardened application is preserved after remediation. We evaluated the pipeline on five real-world agentic applications, as well as on the AgentDojo benchmark. Across all applications, the proposed pipeline identified recurring leakage-enabling patterns and generated patches that can be integrated without disrupting the intended application behavior. The resulting modifications of application code were shown to eliminate leaks when targeted by basic jailbreak and instruction-override attacks, achieving a 100% reduction in leakage, and reduce leaks by 91% under conditions of stress-induced manipulation, without the need of continuous runtime policy enforcement.
Akansha Shukla, Emily Bellov, P. Gandhi et al.· arXiv.org· 0 citations
It is argued that adversarial vulnerability stems from the absence of boundary verification, a security primitive that enforces explicit validation of data as it crosses inter-agent boundaries, including content, identity, execution intent, and state integrity.
Faisal Haque Bappy, Tahrim Hossain, T. S. Zaman et al.· 0 citations
A systematic evaluation of malicious issue requests against state-of-the-art coding agents powered by two major model families reveals critical vulnerabilities in the as-deployed modern coding agents, highlighting the urgent need for stronger agent- and model-level safety mechanisms to protect AI coding agents.
Ankur Singh, Jinqiu Yang, T. Chen· arXiv.org· 2 citations
AlIBI is presented, an automated adaptive black-box attack framework that generates and iteratively refines adversarial comments using detector reasoning and feedback and is motivated to motivate security-aware designs that carefully calibrate trust between natural-language context and program evidence.
Compositional Attack Path Scoring (CAPS), a framework engineered to quantify end-to-end multi-hop risks in LLM architectures, establishes a rigorous benchmark for quantitative vulnerability management in complex, agentic LLM environments.
