Results for “Agent”

arXiv (research papers) Roy Betser SI

AgenTRIM: Tool Risk Mitigation for Agentic AI

AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We characterize these failures as unbalanced tool-driven agency. Agents may retain unnecessary permissions (excessive agency) or fail to invoke required tools (insufficient agency), amplifying the attack surface and reducing performance. We…

Read at arXiv (research papers)

arXiv (research papers) Yi Liu SI

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute with implicit trust and minimal vetting, creating a significant yet uncharacterized attack surface. We conduct the first large-scale empirical security analysis of this emerging ecosystem, collecting 42,447 skills from two major marketplaces…

Read at arXiv (research papers)

arXiv (research papers) Hao Li SI

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack

Large Language Models (LLMs) have enabled the development of powerful agentic systems capable of automating complex workflows across various fields. However, these systems are highly vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external data can hijack agent behavior. In this work, we present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks. The core idea of ReasAlign is to…

Read at arXiv (research papers)

arXiv (research papers) Yutao Mou SI

ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback

While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation behaviors in real time and proactively intervening before unsafe execution is critical for agent deployment, yet remains under-explored. In this work, we first construct TS-Bench, a novel benchmark for step-level tool invocation safety detection in LLM agents. We then develop a guardrail model…

Read at arXiv (research papers)

arXiv (research papers) Hanna Foerster SI

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents

AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior. Among proposed defenses, architectural isolation provides the strongest guarantees by strictly separating trusted task planning from untrusted environment observations. However, applying this design to Computer Use Agents (CUAs), which automate tasks by viewing screens and executing actions, presents a fundamental challenge. Current agents require continuous observation of…

Read at arXiv (research papers)

Simon Willison SI

Claude Cowork Exfiltrates Files

Claude Cowork Exfiltrates Files Claude Cowork defaults to allowing outbound HTTP traffic to only a specific list of domains, to help protect the user against prompt injection attacks that exfiltrate their data. Prompt Armor found a creative workaround: Anthropic's API domain is on that list, so they constructed an attack that includes an attacker's own Anthropic API key and has the agent upload any files it can see to the https://api.anthropic.com/v1/files endpoint, allowing…

Read at Simon Willison

Simon Willison SI

First impressions of Claude Cowork, Anthropic's general agent

New from Anthropic today is Claude Cowork, a "research preview" that they describe as "Claude Code for the rest of your work". It's currently available only to Max subscribers ($100 or $200 per month plans) as part of the updated Claude Desktop macOS application. Update 16th January 2026: it's now also available to $20/month Claude Pro subscribers. I've been saying for a while now that Claude Code is a "general agent" disguised as a developer tool. It can help you with any…

Read at Simon Willison

arXiv (research papers) Xinyi Wu SI

When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent

Web agents, powered by large language models (LLMs), are increasingly deployed to automate complex web interactions. The rise of open-source frameworks (e.g., Browser Use, Skyvern-AI) has accelerated adoption, but also broadened the attack surface. While prior research has focused on model threats such as prompt injection and backdoors, the risks of social engineering remain largely unexplored. We present the first systematic study of social engineering attacks against web…

Read at arXiv (research papers)

arXiv (research papers) Junda Lin SI

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit

LLM agents operating in open environments face escalating risks from indirect prompt injection, particularly within the tool stream where manipulated metadata and runtime feedback hijack execution flow. Existing defenses encounter a critical dilemma as advanced models prioritize injected rules due to strict alignment while static protection mechanisms sever the feedback loop required for adaptive reasoning. To reconcile this conflict, we propose \textbf{VIGIL}, a framework…

Read at arXiv (research papers)

arXiv (research papers) Zhi Yang SI

FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments

Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to plan, invoke tools, and manipulate mutable state introduce new security risks in high-stakes and highly regulated financial environments. However, existing safety evaluations largely focus on language-model-level content compliance or abstract agent settings, failing to capture execution-grounded…

Read at arXiv (research papers)

arXiv (research papers) Qiang Yu SI

Defense Against Indirect Prompt Injection via Tool Result Parsing

As LLM agents transition from digital assistants to physical controllers in autonomous systems and robotics, they face an escalating threat from indirect prompt injection. By embedding adversarial instructions into the results of tool calls, attackers can hijack the agent's decision-making process to execute unauthorized actions. This vulnerability poses a significant risk as agents gain more direct control over physical environments. Existing defense mechanisms against…

Read at arXiv (research papers)

arXiv (research papers) Saad Alqithami SI

Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries

Advances in large language models have enabled agentic AI systems that can reason, plan, and interact with external tools to execute multi-step workflows, while public blockchains have evolved into a programmable substrate for value transfer, access control, and verifiable state transitions. Their convergence introduces a high-stakes systems challenge: designing standard, interoperable, and secure interfaces that allow agents to observe on-chain state, formulate transaction…

Read at arXiv (research papers)

arXiv (research papers) Jingyu Zhang SI

Language Model Agents Under Attack: A Cross Model-Benchmark of Profit-Seeking Behaviors in Customer Service

Customer-service LLM agents increasingly make policy-bound decisions (refunds, rebooking, billing disputes), but the same ``helpful'' interaction style can be exploited: a small fraction of users can induce unauthorized concessions, shifting costs to others and eroding trust in agentic workflows. We present a cross-domain benchmark of profit-seeking direct prompt injection in customer-service interactions, spanning 10 service domains and 100 realistic attack scripts grouped…

Read at arXiv (research papers)

arXiv (research papers) Giuseppe Canale SI

The Silicon Psyche: Anthropomorphic Vulnerabilities in Large Language Models

Large Language Models (LLMs) are rapidly transitioning from conversational assistants to autonomous agents embedded in critical organizational functions, including Security Operations Centers (SOCs), financial systems, and infrastructure management. Current adversarial testing paradigms focus predominantly on technical attack vectors: prompt injection, jailbreaking, and data exfiltration. We argue this focus is catastrophically incomplete. LLMs, trained on vast corpora of…

Read at arXiv (research papers)

arXiv (research papers) Toqeer Ali Syed SI

Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and GraphChain. Nevertheless, this agentic environment increases the probability of the occurrence of multimodal prompt injection (PI) attacks, in which concealed or malicious instructions carried in text, pictures, metadata, or agent-to-agent…

Read at arXiv (research papers)

arXiv (research papers) Armstrong Foundjem SI

Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems

Machine learning (ML) underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box attacks that exploit model comparisons. Larger models can be more vulnerable to introspection-driven jailbreaks and cross-modal manipulation. Traditional cybersecurity lacks ML-specific threat modeling for foundation, multimodal, and RAG…

Read at arXiv (research papers)

arXiv (research papers) Karolina Korgul SI

It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents

Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their reliance on dynamic web content, however, makes them vulnerable to prompt injection attacks: adversarial instructions hidden in interface elements that persuade the agent to divert from its original task. We introduce the Task-Redirecting Agent Persuasion Benchmark (TRAP), a benchmark for studying how persuasion techniques misguide…

Read at arXiv (research papers)

arXiv (research papers) Yihan Wang SI

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs

The integration of Large Language Models (LLMs) into wearable sensing is creating a new class of mobile applications capable of nuanced human activity understanding. However, the reliability of these systems is critically undermined by their vulnerability to prompt injection attacks, where attackers deliberately input deceptive instructions into LLMs. Traditional defenses, based on static filters and rigid rules, are insufficient to address the semantic complexity of these…

Read at arXiv (research papers)

arXiv (research papers) Jaykumar Kasundra SI

AprielGuard

Safeguarding large language models (LLMs) against unsafe or adversarial behavior is critical as they are increasingly deployed in conversational and agentic settings. Existing moderation tools often treat safety risks (e.g. toxicity, bias) and adversarial threats (e.g. prompt injections, jailbreaks) as separate problems, limiting their robustness and generalizability. We introduce AprielGuard, an 8B parameter safeguard model that unify these dimensions within a single…

Read at arXiv (research papers)

Simon Willison SI

Using Claude in Chrome to navigate out the Cloudflare dashboard

I just had my first success using a browser agent - in this case the Claude in Chrome extension - to solve an actual problem. A while ago I set things up so anything served from the https://static.simonwillison.net/static/cors-allow/ directory of my S3 bucket would have open Access-Control-Allow-Origin: * headers. This is useful for hosting files online that can be loaded into web applications hosted on other domains. Problem is I couldn't remember how I did it! I initially…

Read at Simon Willison

arXiv (research papers) Saksham Sahai Srivastava SI

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval

Large Language Model (LLM) agents increasingly rely on long-term memory and Retrieval-Augmented Generation (RAG) to persist experiences and refine future performance. While this experience learning capability enhances agentic autonomy, it introduces a critical, unexplored attack surface, i.e., the trust boundary between an agent's reasoning core and its own past. In this paper, we introduce MemoryGraft. It is a novel indirect injection attack that compromises agent behavior…

Read at arXiv (research papers)

arXiv (research papers) Viet K. Nguyen SI

Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks

Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in chat mode, there is no comparative analysis in multiple models and frameworks. We conducted the first systematic penetration testing and comparative evaluation of agentic AI systems, testing five prominent models (Claude 3.5 Sonnet, Gemini…

Read at arXiv (research papers)

arXiv (research papers) Amy Chang SI

Cisco Integrated AI Security and Safety Framework Report

Artificial intelligence (AI) systems are being readily and rapidly adopted, increasingly permeating critical domains: from consumer platforms and enterprise software to networked systems with embedded agents. While this has unlocked potential for human productivity gains, the attack surface has expanded accordingly: threats now span content safety failures (e.g., harmful or deceptive outputs), model and data integrity compromise (e.g., poisoning, supply-chain tampering)…

Read at arXiv (research papers)

arXiv (research papers) Luoxi Meng SI

ceLLMate: Sandboxing Browser AI Agents

Browser-using agents (BUAs) are an emerging class of AI agents that interact with web browsers in human-like ways, including clicking, scrolling, filling forms, and navigating across pages. While these agents help automate repetitive online tasks, they are vulnerable to prompt injection attacks that trick an agent into performing undesired actions, such as leaking private information or issuing unintended state-changing requests. We propose ceLLMate, a browser-level…

Read at arXiv (research papers)

OWASP GenAI Security Project John Sotiropoulos Security

OWASP Top 10 for Agentic Applications – The Benchmark for Agentic Security in the Age of Autonomous AI

Introducing the OWASP Top 10 for Agentic AI Applications - our community’s actionable framework for securing autonomous, tool-using AI systems. Built at global scale informed by real incidents, and based on our work already adopted across industry, this release marks a pivotal moment in turning insight into action, and advancing the security of Agentic Applications at the pace of innovation.

Read at OWASP GenAI Security Project

OWASP GenAI Security Project Scott Clinton, Project Co-lead Security

OWASP GenAI Security Project Releases Top 10 Risks and Mitigations for Agentic AI Security

Culmination of over 100 industry leaders’ input and extensive published resources to deliver critical guidance to address Agentic AI Security risks WILMINGTON, Del. — Dec. 10, 2025 — The OWASP GenAI Security Project (genai.owasp.org), a leading global open-source and expert community dedicated to delivering practical guidance and tools for securing generative and agentic AI,

Read at OWASP GenAI Security Project

arXiv (research papers) Reachal Wang SI

ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data

Prompt injection attacks aim to contaminate the input data of an LLM to mislead it into completing an attacker-chosen task instead of the intended task. In many applications and agents, the input data originates from multiple sources, with each source contributing a segment of the overall input. In these multi-source scenarios, an attacker may control only a subset of the sources and contaminate the corresponding segments, but typically does not know the order in which the…

Read at arXiv (research papers)

arXiv (research papers) Botao 'Amber' Hu SI

Insured Agents: A Decentralized Trust Insurance Mechanism for Agentic Economy

The emerging "agentic web" envisions large populations of autonomous agents coordinating, transacting, and delegating across open networks. Yet many agent communication and commerce protocols treat agents as low-cost identities, despite the empirical reality that LLM agents remain unreliable, hallucinated, manipulable, and vulnerable to prompt-injection and tool-abuse. A natural response is "agents-at-stake": binding economically meaningful, slashable collateral to…

Read at arXiv (research papers)

arXiv (research papers) Yinan Zhong SI

Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs

Large Language Models (LLMs) have been integrated into many applications (e.g., web agents) to perform more sophisticated tasks. However, LLM-empowered applications are vulnerable to Indirect Prompt Injection (IPI) attacks, where instructions are injected via untrustworthy external data sources. This paper presents Rennervate, a defense framework to detect and prevent IPI attacks. Rennervate leverages attention features to detect the covert injection at a fine-grained token…

Read at arXiv (research papers)

arXiv (research papers) Shiva Gaire SI

Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem

The Model Context Protocol (MCP) has emerged as the de facto standard for connecting Large Language Models (LLMs) to external data and tools, effectively functioning as the "USB-C for Agentic AI." While this decoupling of context and execution solves critical interoperability challenges, it introduces a profound new threat landscape where the boundary between epistemic errors (hallucinations) and security breaches (unauthorized actions) dissolves. This Systematization of…

Read at arXiv (research papers)

Older stories