# Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools

arXiv: https://arxiv.org/abs/2508.02110 · HTML: https://mlsanity.com/paper/2508.02110/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions](https://mlsanity.com/paper/2503.23278/) (2025)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks](https://mlsanity.com/paper/2309.17410/) (2023)
- [A Survey on Trustworthy LLM Agents: Threats and Countermeasures](https://mlsanity.com/paper/2503.09648/) (2025)
- [Conversational Health Agents: A Personalized LLM-Powered Agent Framework](https://mlsanity.com/paper/2310.02374/) (2023)
- [Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification](https://mlsanity.com/paper/2407.20859/) (2024)
- [Imprompter: Tricking LLM Agents into Improper Tool Use](https://mlsanity.com/paper/2410.14923/) (2024)
- [Misusing Tools in Large Language Models With Visual Adversarial Examples](https://mlsanity.com/paper/2310.03185/) (2023)
- [From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection](https://mlsanity.com/paper/2412.10198/) (2024)
- [A Critical Evaluation of Defenses against Prompt Injection Attacks](https://mlsanity.com/paper/2505.18333/) (2025)
- [iAgent: LLM Agent as a Shield between User and Recommender Systems](https://mlsanity.com/paper/2502.14662/) (2025)
- [Attacks on Third-Party APIs of Large Language Models](https://mlsanity.com/paper/2404.16891/) (2024)
- [ICLEval: Evaluating In-Context Learning Ability of Large Language Models](https://mlsanity.com/paper/2406.14955/) (2024)
- [Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System](https://mlsanity.com/paper/2502.11358/) (2025)
- [ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models](https://mlsanity.com/paper/2502.11404/) (2025)

## Built on by (most cited first, 24 of 24)

- [From Storage to Steering: Memory Control Flow Attacks on LLM Agents](https://mlsanity.com/paper/2603.15125/) (2026)
- [SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment](https://mlsanity.com/paper/2604.13630/) (2026)
- [BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models](https://mlsanity.com/paper/2510.00307/) (2025)
- [LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios](https://mlsanity.com/paper/2602.03255/) (2026)
- [STAC: When Innocent Tools Form Dangerous Chains for LLM Agents](https://mlsanity.com/paper/2509.25624/) (2025)
- [Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents](https://mlsanity.com/paper/2606.22504/) (2026)
- [When Skills Lie: Hidden-Comment Injection in LLM Agents](https://mlsanity.com/paper/2602.10498/) (2026)
- [How are AI agents used? Evidence from 177,000 MCP tools](https://mlsanity.com/paper/2603.23802/) (2026)
- [How Adversarial Environments Mislead Agentic AI?](https://mlsanity.com/paper/2604.18874/) (2026)
- [Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs](https://mlsanity.com/paper/2604.03870/) (2026)
- [From Tool Orchestration to Code Execution: A Study of MCP Design Choices](https://mlsanity.com/paper/2602.15945/) (2026)
- [STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems](https://mlsanity.com/paper/2604.10286/) (2026)
- [Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning](https://mlsanity.com/paper/2606.20922/) (2026)
- [Conjunctive Prompt Attacks in Multi-Agent LLM Systems](https://mlsanity.com/paper/2604.16543/) (2026)
- [Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents](https://mlsanity.com/paper/2608.12273/) (2026)
- [ToolFlood: Beyond Selection -- Hiding Valid Tools from LLM Agents via Semantic Covering](https://mlsanity.com/paper/2603.13950/) (2026)
- [ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems](https://mlsanity.com/paper/2604.04426/) (2026)
- [Agent-Facing Information Design in LLM Tool Registries](https://mlsanity.com/paper/2605.23916/) (2026)
- [Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection](https://mlsanity.com/paper/2606.30587/) (2026)
- [ContextLeak: Exfiltrating LLM Agent Context via Malicious Tools](https://mlsanity.com/paper/2608.27800/) (2026)
- [Implicit Manipulation for Skill Selection in LLM Agents with Semantic Matching](https://mlsanity.com/paper/2609.02035/) (2026)
- [A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem](https://mlsanity.com/paper/2609.26761/) (2026)
- [Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems](https://mlsanity.com/paper/2609.30383/) (2026)
- [AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety](https://mlsanity.com/paper/2610.19422/) (2026)

## Abstract (arXiv)

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface, where adversaries can manipulate tool metadata -- such as names, descriptions, and parameter schemas -- to influence agent behavior. We identify this as a new and stealthy threat surface that allows malicious tools to be preferentially selected by LLM agents, without requiring prompt injection or access to model internals. To demonstrate and exploit this vulnerability, we propose the Attractive Metadata Attack (AMA), a black-box in-context learning framework that generates highly attractive but syntactically and semantically valid tool metadata through iterative optimization. The proposed attack integrates seamlessly into standard tool ecosystems and requires no modification to the agent's execution framework. Extensive experiments across ten realistic, simulated tool-use scenarios and a range of popular LLM agents demonstrate consistently high attack success rates (81%-95%) and significant privacy leakage, with negligible impact on primary task execution. Moreover, the attack remains effective even against prompt-level defenses, auditor-based detection, and structured tool-selection protocols such as the Model Context Protocol, revealing systemic vulnerabilities in current agent architectures. These findings reveal that metadata manipulation constitutes a potent and stealthy attack surface. Notably, AMA is orthogonal to injection attacks and can be combined with them to achieve stronger attack efficacy, highlighting the need for execution-level defenses beyond prompt-level and auditor-based mechanisms. Code is available at https://github.com/SEAIC-M/AMA.