Integrity Vulnerabilities

Memory-augmented LLM web agents utilizing raw trajectory memory are vulnerable to Environment-injected Trajectory-based Agent Memory Poisoning (eTAMP). Attackers can embed malicious instructions within user-generated web content (e.g., product pages, forum posts). When the agent processes this content during a routine task, the instructions are passively ingested into its raw trajectory memory. During subsequent, entirely separate tasks on different websites, semantic retrieval mechanisms pull…

A vulnerability in Infrared Vision-Language Models (IR-VLMs) allows attackers to systematically degrade open-ended semantic understanding—compromising classification, captioning, and Visual Question Answering (VQA)—via a physically deployable Universal Curved-Grid Patch (UCGP). Instead of manipulating explicit text labels, the attack disrupts the clean-category manifold in the model's visual representation space by maximizing orthogonal deviation energy from the principal subspace and forcing…

Vision-Language Models (VLMs) are vulnerable to pixel-level adversarial image perturbations. An attacker can inject $\ell_p$-bounded, human-imperceptible noise into an input image to manipulate the model's multi-modal embedding space. This reliably causes the VLM to generate incorrect textual responses, hallucinate non-existent objects, or misclassify subjects, effectively decoupling the model's reasoning from the actual visual evidence. The vulnerability is exploitable via both white-box…

The paper presents a controlled, reproducible evaluation in which untrusted MCP tool descriptions contain hidden instructions that attempt to induce coding agents to access files, invoke other tools, create deceptive links, or execute remote scripts. The authors report that several clients accepted poisoned metadata without adequate validation or parameter visibility; Cursor 1.6.45 was reported unsafe across all four tested vectors. These are paper-reported results from isolated local tests…

OpenClaw is vulnerable to persistent memory poisoning, allowing an attacker to manipulate the agent's long-term memory store (MEMORY.md) via prompt injection. Because the autonomous agent continuously integrates this memory file as context for all subsequent reasoning and task planning, injected payloads act as durable behavioral constraints. This allows an attacker to persistently alter the agent's core policy, manipulate tool selection, and hijack future sessions without any further…

GPT-OSS-Safeguard-20B and Meta-SecAlign (70B/8B) are vulnerable to white-box adversarial attacks generated by automated algorithmic recombination (specifically the claude_v63, claude_v82, and claude_v53-oss optimizers). These algorithms significantly outperform standard discrete optimization methods (like GCG) by integrating continuous optimization (ADC) with LayerNorm gradient scaling (LSGM), or by merging momentum-smoothed gradients with directional perturbation candidate selection (DPTO)…

Multi-Agent Systems based on Large Language Models (LLM-MAS) are vulnerable to systemic Consensus Corruption via cascading error amplification. Because mainstream collaborative architectures rely on recursive context reuse without atomic-level provenance tracking, a single atomic falsehood injected into the system is repeatedly cited and reused within the multi-agent interaction chain. This structural exposure causes the error to deterministically compound across the communication graph…

An imperceptible visual prompt injection vulnerability in Multimodal Large Language Models (MLLMs) allows attackers to execute precise command-hijacking via a Covert Triggered dual-Target Attack (CoTTA). By embedding a bounded, learnable textual overlay ($L_\infty$ norm bound $\varepsilon \le 16$) and adversarial noise into an input image, the attack forces the source image's internal feature representation to align with both the textual and visual embeddings of an attacker-specified…

LLM-as-a-judge systems and automated LLM evaluators are vulnerable to meaning-preserving perturbations, specifically formatting alterations and verbosity manipulations. When grading or classifying text and agentic transcripts, LLM judges exhibit high sensitivity to layout-only changes (such as whitespace and indentation) and response length, frequently altering their scores even when the underlying semantic and factual content remains identical. This allows attackers to bypass automated safety…

Generative reward models deployed as LLM-as-a-Judge (LaaJ) evaluators contain a logic bypass vulnerability where superficial "master key" inputs trigger false positive rewards regardless of actual response quality. Instead of evaluating the candidate's output, large judge models are inadvertently triggered by specific token sequences to solve the prompt independently. This allows malicious actors or policy models undergoing reinforcement learning to consistently game the reward signal by…