arXiv AI
Aug 11
ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
arXiv:2608. 09732v1 Announce Type: cross Abstract: Agent skills are emerging as an important attack surface in LLM-based agent systems.
MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?
Related stories
arXiv AI
Jun 17
SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
arXiv:2602. 14211v3 Announce Type: replace-cross Abstract: Agent skills extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources, improving reusability but creating a new supply-chain attack surface.
arXiv AI
Sep 7
Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection
Repeat-After-Me is a black-box adaptive visual prompt injection technique that can reveal personally identifiable information or trigger malicious tool calls in both open-weight and commercial vision‑language models, achieving attack success rates above 80% on Qwen3.6‑27B and 47% on GPT‑5.5. The method works even when the benign user prompt is unrelated to the injected task and does not explicitly authorize it, and it retains significant effectiveness when transferred across models or optimized on surrogate systems. In a real‑world OpenClaw Discord deployment, a minimally injected image can overwrite TOOLS.md, enabling remote code execution and secret exfiltration.
arXiv AI
Aug 11
SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills
arXiv:2608. 08468v1 Announce Type: cross Abstract: Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security properties remain under-explored.
arXiv AI
Sep 11
An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks
arXiv:2609. 09404v1 Announce Type: cross Abstract: Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services.
arXiv AI
Sep 1
SIR: Self-improving Red-teaming for Compute Use Agents
arXiv:2608.30207v1 Announce Type: cross Abstract: Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal...
arXiv AI
2d ago
Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents
The paper introduces a new skill poisoning technique for large language model agents that decouples the pretext (rationale) from the actuation (operation). By separating these two risk‑realization factors, the authors create coordinated pretext‑actuation skill pairs that allow malicious actions to remain hidden within legitimate agent behavior. An automated framework is presented to discover execution dependencies, synthesize these skill pairs, and refine them through closed‑loop feedback, achieving high attack success in both single‑session and persistent scenarios.
arXiv Computer Vision
Aug 31
Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models
The paper introduces Meta-Adaptive Multimodal Jailbreaking (MAMJ), a method that jointly optimizes an attack strategy prompt and attacker weights to generate more effective jailbreaks against vision‑language models. Using an LLM‑based critique to refine the strategy and group‑level success‑rate rewards to update the weights, MAMJ achieves high attack success rates on MM‑SafetyBench, outperforming existing baselines by up to 24.1 percentage points. The learned attacker also transfers to unseen models and remains robust against typical defenses, highlighting a systemic vulnerability in current VLMs.
arXiv AI
2d ago
ActionGuard: Tool Call Authorization under Poisoned Skills
arXiv:2609.39450v1 Announce Type: cross Abstract: LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. Howe...
Hugging Face Trending Papers
Aug 27
Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models
The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the meta level: template-based attacks freeze the image...
arXiv AI
Sep 11
AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents
The paper introduces an end‑to‑end framework for testing image‑triggered command injection on computer‑use agents (CUAs). It demonstrates that a local visual patch can cause verifiable environmental effects through the entire pipeline—from screenshot input, through vision‑language‑model generation, action parsing, to execution—by training and deploying patches on GitHub Pages and a CSDN clone. Across five open‑source or publicly available GUI‑agent or VLM backends, the study reports 84.5% T‑ASR, 47.0% TAPR, and 20.3% E2E‑ASR success rates, with trajectory analysis revealing that some attacks first execute malicious terminal commands before continuing the original task.
arXiv AI
Jun 29
When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
arXiv:2602. 10179v2 Announce Type: replace-cross Abstract: Recent advances in large image editing models have shifted the paradigm from text-driven instructions to vision-prompt editing, where user intent is inferred directly from visual inputs such as marks, arrows, and visual-text prompts.