Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?

• URL: http://arxiv.org/abs/2510.05244v1
• Date: Mon, 06 Oct 2025 18:09:02 GMT
• Title: Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?
• Authors: Rishika Bhagwatkar, Kevin Kasa, Abhay Puri, Gabriel Huang, Irina Rish, Graham W. Taylor, Krishnamurthy Dj Dvijotham, Alexandre Lacoste,
• Abstract summary: We show that a simple, modular and model-agnostic defense operating at the agent--tool interface achieves perfect security with high utility.<n>We employ a defense based on two firewalls: a Tool-Input Firewall (Minimizer) and a Tool-Output Firewall (Sanitizer)
• Score: 58.48689960350828
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause unintended or harmful behavior. Inspired by the well-established concept of firewalls, we show that a simple, modular and model-agnostic defense operating at the agent--tool interface achieves perfect security (0% or the lowest possible attack success rate) with high utility (task success rate) across four public benchmarks: AgentDojo, Agent Security Bench, InjecAgent and tau-Bench, while achieving a state-of-the-art security-utility tradeoff compared to prior results. Specifically, we employ a defense based on two firewalls: a Tool-Input Firewall (Minimizer) and a Tool-Output Firewall (Sanitizer). Unlike prior complex approaches, this firewall defense makes minimal assumptions on the agent and can be deployed out-of-the-box, while maintaining strong performance without compromising utility. However, our analysis also reveals critical limitations in these existing benchmarks, including flawed success metrics, implementation bugs, and most importantly, weak attacks, hindering significant progress in the field. To foster more meaningful progress, we present targeted fixes to these issues for AgentDojo and Agent Security Bench while proposing best-practices for more robust benchmark design. Further, we demonstrate that although these firewalls push the state-of-the-art on existing benchmarks, it is still possible to bypass them in practice, underscoring the need to incorporate stronger attacks in security benchmarks. Overall, our work shows that existing agentic security benchmarks are easily saturated by a simple approach and highlights the need for stronger agentic security benchmarks with carefully chosen evaluation metrics and strong adaptive attacks.

Related papers

• Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening [23.066685616914807]
  We argue that effective agent security should be intrinsic and selective rather than architecturally decoupled and mandatory.<n>We propose Spider-Sense framework, which allows agents to maintain latent vigilance and trigger defenses only upon risk perception.<n>Spider-Sense achieves competitive or superior defense performance, attaining the lowest Attack Success Rate (ASR) and False Positive Rate (FPR)
  arXiv  Detail & Related papers  (2026-02-05T07:11:05Z)
• AgentDyn: A Dynamic Open-Ended Benchmark for Evaluating Prompt Injection Attacks of Real-World Agent Security System [44.50700894734539]
  We introduce AgentDyn, a benchmark featuring 60 challenging open-ended tasks and 560 injection test cases.<n>Unlike prior static benchmarks, AgentDyn requires dynamic planning and incorporates helpful third-party instructions.<n>Our evaluation of ten state-of-the-art defenses suggests that almost all existing defenses are either not secure enough or suffer from significant over-defense.
  arXiv  Detail & Related papers  (2026-02-03T05:20:42Z)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents [60.98294016925157]
  AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss.<n>We introduce Single-Shot Planning for CUAs, where a trusted planner generates a complete execution graph with conditional branches before any observation of potentially malicious content.<n>Although this architectural isolation successfully prevents instruction injections, we show that additional measures are needed to prevent Branch Steering attacks.
  arXiv  Detail & Related papers  (2026-01-14T23:06:35Z)
• PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance [10.105673138616483]
  Large Language Models (LLMs) are increasingly integrated into real-world applications, from virtual assistants to autonomous agents.<n>As attackers evolve with paraphrased, obfuscated, and even multi-task injection strategies, existing benchmarks are no longer sufficient to capture the full spectrum of emerging threats.<n>We propose PromptSleuth, a semantic-oriented defense framework that detects prompt injection by reasoning over task-level intent rather than surface features.
  arXiv  Detail & Related papers  (2025-08-28T15:19:07Z)
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• DoomArena: A framework for Testing AI Agents Against Evolving Security Threats [81.73540246946015]
  We present DoomArena, a security evaluation framework for AI agents.<n>It is a plug-in framework and integrates easily into realistic agentic frameworks.<n>It is modular and decouples the development of attacks from details of the environment in which the agent is deployed.
  arXiv  Detail & Related papers  (2025-04-18T20:36:10Z)
• GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks [14.558728517191044]
  We introduce a novel prompt injection attack detection method, GenTel-Shield, along with a comprehensive evaluation benchmark, GenTel-Bench. To prove the effectiveness of GenTel-Shield, we evaluate it together with vanilla safety guardrails against the GenTel-Bench dataset. Empirically, GenTel-Shield can achieve state-of-the-art attack detection success rates, which reveals the critical weakness of existing safeguarding techniques.
  arXiv  Detail & Related papers  (2024-09-29T02:35:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.