Overview

Prompt injection attacks exploit the fact that language models may treat instructions embedded in untrusted text, images, tool outputs, or stored memory as authoritative. Researchers test attacks in settings such as web browsing, coding, peer review, and computer use, using adaptive payloads, visual or other hidden carriers, and multi-turn scenarios. Defenses range from input detection and adversarial training to provenance tracking, restricted tool permissions, and deterministic checks outside the model. A central challenge is resisting attacks that change across tasks and interfaces without blocking legitimate work; model refusals alone are often not a dependable security boundary.

Latest papers

94 papers4 papers in the last four weeks, down 73% on the four weeks before. 0.0% of all new papers.

Nov 3, 2025

"Give a Positive Review Only": An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers

With the rapid advancement of AI models, their deployment across diverse tasks has become increasingly widespread. A notable emerging application is leveraging AI models to assist in reviewing scientific papers. However, recent reports have revealed that some papers contain hidden, injected prompts designed to manipulate AI reviewers into providing overly favorable evaluations. In this work, we present an early systematic investigation into this emerging threat. We propose two classes of attacks: (1) static attack, which employs a fixed injection prompt, and (2) iterative attack, which optimizes the injection prompt against a simulated reviewer model to maximize its effectiveness. Both attacks achieve striking performance, frequently inducing full evaluation scores when targeting frontier AI reviewers. Furthermore, we show that these attacks are robust across various settings. To counter this threat, we explore a simple detection-based defense. While it substantially reduces the attack success rate, we demonstrate that an adaptive attacker can partially circumvent this defense. Our findings underscore the need for greater attention and rigorous safeguards against prompt-injection threats in AI-assisted peer review.
Oct 5, 2025

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents

Multimodal agents built on large vision-language models are increasingly deployed in open-world settings but remain highly vulnerable to prompt injection. Typographic text-in-image attacks such as FigStep have been evaluated mainly on standalone vision-language models. For agents, user goals, webpage context, and action history make the effect of embedded instructions uncertain, and robustness to behavior-guided, adaptive visual injections remains insufficiently studied. We introduce AgentTypo, a black-box red-teaming framework that launches adaptive typographic prompt injection by embedding optimized text into webpage images. We formulate an attention-guided automatic typographic prompt-injection objective that favors the attacker's expected answer over the clean-page answer, together with task-conditioned visual attention from small question-answering models. A novel black-box optimization method searches text position, contrast, and color. To further strengthen the attack, we develop a multi-LLM system that iteratively refines injection prompts using evaluation feedback and retrieves successful past examples for strategy learning. Experiments on the VWA-Adv and Mind2Web benchmarks show that AgentTypo significantly outperforms state-of-the-art image-based prompt injection attacks. Across seven closed- and open-source model backends, AgentTypo-pro achieves 45%-83% ASR, outperforming the CLIP-based AgentAttack by 29-47% and previous typographic attacks by 25%-37% on VWA-Adv.
Oct 1, 2025

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents

Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none have been systematically evaluated for web agents. In this work, we bridge this gap by presenting the first comprehensive benchmark study on detecting prompt injection attacks targeting web agents. We begin by introducing a fine-grained categorization of such attacks based on the threat model. We then construct datasets containing both malicious and benign samples: malicious text segments generated by different attacks, benign text segments from four categories, malicious images produced by attacks, and benign images from two categories. Next, we systematize both text-based and image-based detection methods. Finally, we evaluate their performance across multiple scenarios. Our key findings show that while some detectors can identify attacks that rely on explicit textual instructions or visible image perturbations with moderate to high accuracy, they largely fail against attacks that omit explicit instructions or employ imperceptible perturbations. Our datasets and code are released at: https://github.com/Norrrrrrr-lyn/WAInjectBench.
Sep 6, 2025

Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment

Coding agents powered by large language models are becoming central modules of modern IDEs, helping users perform complex tasks by invoking tools. While powerful, tool invocation opens a substantial attack surface. Prior work has demonstrated attacks against general-purpose and domain-specific agents, but none have focused on the security risks of tool invocation in coding agents. To fill this gap, we conduct the first systematic red-teaming of six popular real-world coding agents: Cursor, Claude Code, Copilot, Windsurf, Cline, and Trae. Our red-teaming proceeds in two phases. In Phase 1, we perform prompt leakage reconnaissance to recover system prompts. We discover a general vulnerability, ToolLeak, which allows malicious prompt exfiltration through benign argument retrieval during tool invocation. In Phase 2, we hijack the agent's tool-invocation behavior using a novel two-channel prompt injection in the tool description and return values, achieving remote code execution (RCE). We adaptively construct payloads using security information leaked in Phase 1. In emulation across five backends, our method outperforms baselines on Claude-Sonnet-4, Claude-Sonnet-4.5, Grok-4, and GPT-5. On real agents, our approach succeeds on 19 of 25 agent-LLM pairs, achieving leakage on every agent using Claude and Grok backends. For tool-invocation hijacking, we obtain RCE on every tested agent-LLM pair, with our two-channel method delivering the highest success rate. We provide case studies on Cursor and Claude Code, analyze security guardrails of external and built-in tools, and conclude with practical defense recommendations.