cập nhật 1 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.2 giờ sau khi CVE được công bố (n = 5307, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
Security teams want to spot unusual AI agent behavior while they’re still defining normal
🛡️ Tin bảo mật Help Net Security 12 ngày trước

AI agents topped the list of planned investments in behavioral monitoring in Abnormal AI’s 2026 State of Behavioral Security Report. Asked where their organizations would invest most over the next two years, 43% of respondents chose AI agents, more than three times the share who …

🅱 hạng B
28
Over 575 malicious OpenClaw skills delivered malware to Windows and macOS
🛡️ Tin bảo mật Help Net Security 12 ngày trước

Cybercriminals are using AI agents to coordinate attacks, stolen credentials to access linked services, and tools that interfere with intrusion detection and system recovery, according to Acronis TRU Cyber Pulse 2026. One operator coordinates activity across several countries In …

🅱 hạng B
28
Tail-risk-aware Agent Safety: Constraining Tail Risks Across Multi-step LLM Agent Workflows
📄 Paper arXiv cs.AI 12 ngày trước

arXiv:2611.10411v1 Announce Type: new Abstract: LLM-based agents extend LLMs with tool calls, memory, planning, and retrieval to act in external environments, but they are vulnerable to attacks at different workflow steps. Existing defenses, including prompt engineering and post…

🅲 hạng C
28
The Devil Wears Markdown: Detecting Malicious Intent Hidden in AI Agent Skill Instructions through Hybrid Static, Dynamic, and Agentic Analysis
📄 Paper arXiv cs.CR 12 ngày trước

arXiv:2611.10830v1 Announce Type: new Abstract: Agentic AI ecosystems increasingly rely on reusable agent skills that combine executable code, natural-language instructions, configuration artifacts, and external tool integrations. These hybrid artifacts create software supply-ch…

🅲 hạng C
28
Tracing MCP Security Vulnerabilities: Constructing and Analyzing an MCP Security Vulnerability Dataset
📄 Paper arXiv cs.CR 12 ngày trước

arXiv:2611.11104v1 Announce Type: new Abstract: As a core protocol for integrating large language models (LLMs) with external data sources and tools, the Model Context Protocol (MCP) has quickly become a key interface in emerging AI agent systems. As the MCP ecosystem expands, r…

🅲 hạng C
28
Agentic Attribution of Cloud Resource Ownership
📄 Paper arXiv cs.CR 12 ngày trước

arXiv:2611.11340v1 Announce Type: new Abstract: Security tools raise findings across cloud environments, and AI agents now investigate and prioritize them. A finding is still resolved by people: it has to reach the people responsible for fixing it and accountable for the resourc…

🅲 hạng C
28
ARTEX goes from pentesting tool to attacker staple in three months
🛡️ Tin bảo mật Help Net Security 12 ngày trước

A security researcher’s AI agent breached an internal sales application used by WorkOS’s go-to-market teams, the developer platform provider confirmed on Friday. “The researcher was conducting cybersecurity benchmark evaluations using ARTEX when their agent escaped its isolated t…

🅱 hạng B
28
Wirken: Open-source AI agent gateway
🛡️ Tin bảo mật Help Net Security 13 ngày trước

Wirken is an open-source gateway that sits between messaging apps and AI agents. It assumes any agent can be turned against its owner and limits what a compromised one can reach. Take an agent that reads your chats and email, holds the keys to your accounts and can run commands. …

🅱 hạng B
⚪ Mức độ: CHƯA ĐỦ DỮ LIỆU · RCE
Dùng để khai thác: chạy mã tuỳ ý trên máy chủ — thường là chiếm quyền cao nhất, không cần người dùng bấm gì
Hậu quả: chiếm toàn bộ máy chủ
🎯 Kẻ tấn công làm gì (từng bước)
  1. Tìm đúng đường dẫn/API có xử lý dữ liệu người dùng gửi lên
  2. Gửi payload đã chế để máy chủ thực thi lệnh/mã
  3. Dùng quyền của tiến trình web để đọc file, cài backdoor, mở kênh ra ngoài
🔍 Dấu hiệu bị tấn công (để kiểm tra log)
  • Tiến trình web (php-fpm/nginx/java) sinh tiến trình con bất thường: sh, bash, curl, wget
  • Kết nối ra ngoài từ máy chủ tới IP lạ đúng lúc có request lạ
  • File mới xuất hiện trong thư mục tải lên/tạm
🛡 Phòng ngay (làm được hôm nay)
  • Vá ngay bản có lỗi (ưu tiên số 1)
  • Chặn tạm đường dẫn/API bị lỗi ở WAF/reverse proxy nếu chưa vá được
  • Chạy tiến trình web bằng user quyền thấp, tắt các hàm shell (disable_functions) nếu dùng PHP
  • Bật giám sát tiến trình con của web server để phát hiện lệnh lạ
→ Theo dõi và vá theo lịch; chưa thấy dấu hiệu bị khai thác.
28
GuardrailAgent: An Agentic Framework for Jailbreak Defense
📄 Paper arXiv cs.CR 13 ngày trước

arXiv:2611.09734v1 Announce Type: new Abstract: Despite undergoing safety training to align with human values, large language models (LLMs) remain vulnerable to jailbreak attacks that circumvent built-in safeguards and elicit malicious behaviors given by the adversary. Existing …

🅲 hạng C
28
Aegis OS: A Transactional Multi-Tenant Operating System Runtime for Eliminating Authorization Fatigue in Autonomous Coding Agents
📄 Paper arXiv cs.CR 13 ngày trước

arXiv:2611.08516v1 Announce Type: cross Abstract: Autonomous coding agents such as Google Antigravity (agy), Anthropic Claude Code (claude), and OpenAI Codex CLI (codex) execute multi-step software engineering workflows on workstations and cloud hosts. Existing agent environment…

🅲 hạng C
28
OpenAI’s GPT-6 Cyber found 81 Firefox flaws earlier AI testing missed
💥 Lỗ hổng / Exploit Help Net Security 15 ngày trước

OpenAI has introduced GPT-6 Cyber, a version of GPT-6 Astra trained to find software vulnerabilities, test how attackers could exploit them, and help develop fixes. The model is designed for authorized security testing of websites and applications. Vulnerability research and secu…

🅱 hạng B
28
Trust Responsive Runtime Authorization for Agentic AI with Empirical Characterization of Policy Behavior and Parameter Sensitivity
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.06996v1 Announce Type: new Abstract: The policy that converts runtime estimates of an autonomous agent's condition into operational authority is rarely specified or measured. We empirically characterize the Trust Responsive Authorization Policy (TRAP), which maps an A…

🅲 hạng C
28
EnvOpt: Automated Optimization for Agent Environments
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.07372v1 Announce Type: new Abstract: An LLM agent's cost and success depend on its model, its harness, and its environment. In addition to the widely studied directions of parameter tuning and harness optimization, we propose the third direction: optimization over sta…

🅲 hạng C
28
DelegateEval: Evaluating Platforms for Personal External Service Agents
📄 Paper arXiv cs.AI 16 ngày trước

arXiv:2611.07508v1 Announce Type: new Abstract: AI agents that work for an individual over time may also help that individual serve external clients. We define a personal external service agent as an agent authorized and continuously managed by a specific individual to accept cl…

🅲 hạng C
28
A Gingerbread House for LLM Agents: Source-Planned Honeypots That Lure Autonomous Attackers into an Isolated Shadow
📄 Paper arXiv cs.CR 16 ngày trước

arXiv:2611.07611v1 Announce Type: new Abstract: LLM agents can exploit web vulnerabilities fast enough that patching may come too late. Deception against such agents has mostly lured them away from a real target that stays reachable. We study a different arrangement: an LLM defe…

🅲 hạng C
28
AI agent detection signals that still work when agents look human
🛡️ Tin bảo mật Help Net Security 17 ngày trước

Bots follow a script. AI agents work toward a goal and choose their own steps, which makes them harder to catch. In this Help Net Security interview, Zohaib Ahmed, CEO of Resemble AI explains how agents arrive as declared, undeclared or disguised traffic, and why binary bot detec…

🅱 hạng B
28
Most consumers aren’t ready to let AI agents shop unsupervised
🛡️ Tin bảo mật Help Net Security 17 ngày trước

Customer control, account security and ease of use are influencing the adoption of AI agents that make purchases, book services and access personal information, according to Okta’s 2026 Customer Identity Trends Report. Consumers’ willingness to delegate depends on what an agent c…

🅱 hạng B
28
VirtualTrialHarness: Coordinating Agentic Operationalization of Virtual Trial Protocols Across Complex Clinical Schemas
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2611.05551v1 Announce Type: new Abstract: Virtual trials use routinely collected clinical data to evaluate treatment strategies, but translating a study protocol into an executable analysis requires determining how clinical concepts and study requirements should be represe…

🅲 hạng C
28
ViBench 2.0: A Benchmark for Long-Horizon Software Building
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2611.05620v1 Announce Type: new Abstract: On Replit, our agentic engineering platform, users now build entire products without writing code, through successive feature requests to an agent. Yet existing coding benchmarks evaluate single, fully specified tasks, and many are…

🅲 hạng C
28
Agents, Think Only When it Helps
📄 Paper arXiv cs.AI 17 ngày trước

arXiv:2611.05709v1 Announce Type: new Abstract: LLM agent distillation transfers agentic capabilities to student models by training on complete teacher trajectories that typically interleave thoughts and actions. We question how critical thought supervision is for agents' ultima…

🅲 hạng C