# How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

arXiv: https://arxiv.org/abs/2603.15714 · HTML: https://mlsanity.com/paper/2603.15714/

## Key facts

- Cited by 17 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 45 of its 63 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Placed in

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

## Builds on (most cited first, 30 of 45)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts](https://mlsanity.com/paper/2311.05608/) (2023)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [SecAlign: Defending Against Prompt Injection with Preference Optimization](https://mlsanity.com/paper/2410.05451/) (2024)
- [Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming](https://mlsanity.com/paper/2501.18837/) (2025)
- [Image Hijacks: Adversarial Images can Control Generative Models at Runtime](https://mlsanity.com/paper/2309.00236/) (2023)
- [WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks](https://mlsanity.com/paper/2504.18575/) (2025)
- [The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections](https://mlsanity.com/paper/2510.09023/) (2025)
- [OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents](https://mlsanity.com/paper/2506.14866/) (2025)
- [Best-of-N Jailbreaking](https://mlsanity.com/paper/2412.03556/) (2024)

## Built on by (most cited first, 17 of 17)

- [Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs](https://mlsanity.com/paper/2603.24511/) (2026)
- [GPT-Red: Automated Red Teaming via Self-Play at Scale](https://mlsanity.com/paper/2607.26115/) (2026)
- [Assessing Automated Prompt Injection Attacks in Agentic Environments](https://mlsanity.com/paper/2606.10525/) (2026)
- [Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation](https://mlsanity.com/paper/2606.10749/) (2026)
- [Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States](https://mlsanity.com/paper/2608.02657/) (2026)
- [Bounded Agents: Delegation Security for Multi-Agent AI Systems](https://mlsanity.com/paper/2608.15888/) (2026)
- [Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs](https://mlsanity.com/paper/2604.03870/) (2026)
- [When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models](https://mlsanity.com/paper/2605.27851/) (2026)
- [Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming](https://mlsanity.com/paper/2607.11698/) (2026)
- [ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents](https://mlsanity.com/paper/2605.17324/) (2026)
- [Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming](https://mlsanity.com/paper/2608.05108/) (2026)
- [GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines](https://mlsanity.com/paper/2606.09935/) (2026)
- [Steerability via constraints: a substrate for scalable oversight of coding agents](https://mlsanity.com/paper/2607.02389/) (2026)
- [Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows](https://mlsanity.com/paper/2607.13078/) (2026)
- [Toward Metacognitive One-Shot Indirect Prompt Injection: Strategy Abstraction Via Outcome-Conditioned Reflection](https://mlsanity.com/paper/2608.08795/) (2026)
- [When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systems](https://mlsanity.com/paper/2609.23700/) (2026)
- [The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems](https://mlsanity.com/paper/2609.27155/) (2026)

## Abstract (arXiv)

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness. A critical but underexplored dimension of this threat is concealment: since users tend to observe only an agent's final response, an attack can conceal its existence by presenting no clue of compromise in the final user facing response while successfully executing harmful actions. This leaves users unaware of the manipulation and likely to accept harmful outcomes as legitimate. We present findings from a large scale public red teaming competition evaluating this dual objective across three agent settings: tool calling, coding, and computer use. The competition attracted 464 participants who submitted 272000 attack attempts against 13 frontier models, yielding 8648 successful attacks across 41 scenarios. All models proved vulnerable, with attack success rates ranging from 0.5% (Claude Opus 4.5) to 8.5% (Gemini 2.5 Pro). We identify universal attack strategies that transfer across 21 of 41 behaviors and multiple model families, suggesting fundamental weaknesses in instruction following architectures. Capability and robustness showed weak correlation, with Gemini 2.5 Pro exhibiting both high capability and high vulnerability. To address benchmark saturation and obsoleteness, we will endeavor to deliver quarterly updates through continued red teaming competitions. We open source the competition environment for use in evaluations, along with 95 successful attacks against Qwen that did not transfer to any closed source model. We share model-specific attack data with respective frontier labs and the full dataset with the UK AISI and US CAISI to support robustness research.