# From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection

arXiv: https://arxiv.org/abs/2412.10198 · HTML: https://mlsanity.com/paper/2412.10198/

## Key facts

- Cited by 38 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 22 of its 28 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## 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, 22 of 22)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages](https://mlsanity.com/paper/2402.10753/) (2024)
- [Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum](https://mlsanity.com/paper/2308.14034/) (2023)
- [Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning](https://mlsanity.com/paper/2405.15114/) (2024)
- [ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks](https://mlsanity.com/paper/2310.12516/) (2023)
- [CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution](https://mlsanity.com/paper/2306.06755/) (2023)

## Built on by (most cited first, 30 of 38)

- [Prompt Injection Attack to Tool Selection in LLM Agents](https://mlsanity.com/paper/2504.19793/) (2025)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems](https://mlsanity.com/paper/2506.13666/) (2025)
- [Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools](https://mlsanity.com/paper/2508.02110/) (2025)
- [AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition](https://mlsanity.com/paper/2602.11348/) (2026)
- [Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools](https://mlsanity.com/paper/2509.21011/) (2025)
- [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)
- [Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2506.06151/) (2025)
- [A Vision for Access Control in LLM-based Agent Systems](https://mlsanity.com/paper/2510.11108/) (2025)
- [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)
- [BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models](https://mlsanity.com/paper/2510.00307/) (2025)
- [SoK: Trust-Authorization Mismatch in LLM Agent Interactions](https://mlsanity.com/paper/2512.06914/) (2025)
- [Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System](https://mlsanity.com/paper/2502.11358/) (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)
- [MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning](https://mlsanity.com/paper/2605.26154/) (2026)
- [AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents](https://mlsanity.com/paper/2603.07557/) (2026)
- [Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments](https://mlsanity.com/paper/2605.27209/) (2026)
- [Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment](https://mlsanity.com/paper/2509.05755/) (2025)
- [Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation](https://mlsanity.com/paper/2506.03535/) (2025)
- [Agents at Risk: How Users Unwittingly Undermine LLM Safety](https://mlsanity.com/paper/2601.10758/) (2026)
- [Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search](https://mlsanity.com/paper/2603.24203/) (2026)
- [GAMMAF: A Common Framework for Graph-Based Anomaly Monitoring Benchmarking in LLM Multi-Agent Systems](https://mlsanity.com/paper/2604.24477/) (2026)
- [Can LLMs Threaten Human Survival? Benchmarking Potential Existential Threats from LLMs via Prefix Completion](https://mlsanity.com/paper/2511.19171/) (2025)
- [Assertion-Conditioned Compliance: A Provenance-Aware Vulnerability in Multi-Turn Tool-Calling Agents](https://mlsanity.com/paper/2512.00332/) (2025)
- [ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems](https://mlsanity.com/paper/2604.04426/) (2026)
- [Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning](https://mlsanity.com/paper/2605.09822/) (2026)
- [Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures](https://mlsanity.com/paper/2605.25435/) (2026)

## Abstract (arXiv)

Tool-calling has changed Large Language Model (LLM) applications by integrating external tools, significantly enhancing their functionality across diverse tasks. However, this integration also introduces new security vulnerabilities, particularly in the tool scheduling mechanisms of LLM, which have not been extensively studied. To fill this gap, we present ToolCommander, a novel framework designed to exploit vulnerabilities in LLM tool-calling systems through adversarial tool injection. Our framework employs a well-designed two-stage attack strategy. Firstly, it injects malicious tools to collect user queries, then dynamically updates the injected tools based on the stolen information to enhance subsequent attacks. These stages enable ToolCommander to execute privacy theft, launch denial-of-service attacks, and even manipulate business competition by triggering unscheduled tool-calling. Notably, the ASR reaches 91.67% for privacy theft and hits 100% for denial-of-service and unscheduled tool calling in certain cases. Our work demonstrates that these vulnerabilities can lead to severe consequences beyond simple misuse of tool-calling systems, underscoring the urgent need for robust defensive strategies to secure LLM Tool-calling systems.