# ToolTweak: An Attack on Tool Selection in LLM-based Agents

arXiv: https://arxiv.org/abs/2510.02554 · HTML: https://mlsanity.com/paper/2510.02554/

## Key facts

- Cited by 26 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 28 of its 46 references that are in the map.
- First posted on arXiv 2 Oct 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, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2402.07867/) (2024)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [From Sparse to Soft Mixtures of Experts](https://mlsanity.com/paper/2308.00951/) (2023)
- [Prompt Injection Attack to Tool Selection in LLM Agents](https://mlsanity.com/paper/2504.19793/) (2025)
- [Best-of-N Jailbreaking](https://mlsanity.com/paper/2412.03556/) (2024)
- [ToolGen: Unified Tool Retrieval and Calling via Generation](https://mlsanity.com/paper/2410.03439/) (2024)
- [Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text](https://mlsanity.com/paper/2506.07001/) (2025)
- [BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models](https://mlsanity.com/paper/2510.00307/) (2025)

## Built on by (most cited first, 26 of 26)

- [Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems](https://mlsanity.com/paper/2604.03081/) (2026)
- [AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems](https://mlsanity.com/paper/2603.15727/) (2026)
- [When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents](https://mlsanity.com/paper/2606.05806/) (2026)
- [MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP](https://mlsanity.com/paper/2601.07395/) (2026)
- [When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents](https://mlsanity.com/paper/2606.20023/) (2026)
- [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)
- [Toward a Safe Internet of Agents](https://mlsanity.com/paper/2512.00520/) (2025)
- [From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills](https://mlsanity.com/paper/2607.01456/) (2026)
- [Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening](https://mlsanity.com/paper/2605.28999/) (2026)
- [Intent-Governed Tool Authorization for AI Agents](https://mlsanity.com/paper/2606.22916/) (2026)
- [Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning](https://mlsanity.com/paper/2606.20922/) (2026)
- [Can LLMs Threaten Human Survival? Benchmarking Potential Existential Threats from LLMs via Prefix Completion](https://mlsanity.com/paper/2511.19171/) (2025)
- [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)
- [Do LLMs Favor Their Providers? Measuring Vertical Integration Bias in Code Generation](https://mlsanity.com/paper/2605.28515/) (2026)
- [A Security Analysis of Long-Horizon Agentic AI Systems: Threats, Evaluation, and Framework Development](https://mlsanity.com/paper/2606.14816/) (2026)
- [Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents](https://mlsanity.com/paper/2607.19837/) (2026)
- [MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps](https://mlsanity.com/paper/2608.17659/) (2026)
- [WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents](https://mlsanity.com/paper/2608.24017/) (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)
- [SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents](https://mlsanity.com/paper/2609.35889/) (2026)
- [Surviving the Router: Optimizing Skill Injections for Retrieval and Execution](https://mlsanity.com/paper/2610.08098/) (2026)
- [Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions](https://mlsanity.com/paper/2610.14334/) (2026)
- [Same Attack, Different Judge: A First Controlled Adversarial Comparison of Jev, LLM Judges, and Purpose-Built Safety Classifiers](https://mlsanity.com/paper/2610.17820/) (2026)

## Abstract (arXiv)

As LLMs increasingly power agents that interact with external tools, tool use has become an essential mechanism for extending their capabilities. These agents typically select tools from growing databases or marketplaces to solve user tasks, creating implicit competition among tool providers and developers for visibility and usage. In this paper, we show that this selection process harbors a critical vulnerability: by iteratively manipulating tool names and descriptions, adversaries can systematically bias agents toward selecting specific tools, gaining unfair advantage over equally capable alternatives. We present ToolTweak, a lightweight automatic attack that increases selection rates from a baseline of around 20% to as high as 81%, with strong transferability between open-source and closed-source models. Beyond individual tools, we show that such attacks cause distributional shifts in tool usage, revealing risks to fairness, competition, and security in emerging tool ecosystems. To mitigate these risks, we evaluate two defenses: paraphrasing and perplexity filtering, which reduce bias and lead agents to select functionally similar tools more equally. All code will be open-sourced upon acceptance.