🧩 Chức năng: Tự động hoá quy trình
PaperOrchestra là một khung đa tác nhân tự động cho việc viết bài nghiên cứu AI, giúp lập trình viên và nhà nghiên cứu tạo nội dung tài liệu khoa học một cách nhanh chóng và hiệu quả.
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5473, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
🧩 Chức năng: Tự động hoá quy trình
PaperOrchestra là một khung đa tác nhân tự động cho việc viết bài nghiên cứu AI, giúp lập trình viên và nhà nghiên cứu tạo nội dung tài liệu khoa học một cách nhanh chóng và hiệu quả.
arXiv:2611.22223v1 Announce Type: new Abstract: Large Language Model (LLM)-based web agents rely on data minimization and least privilege to protect user privacy. We show that these principles are necessary but insufficient: they constrain authorized sources, but not higher-sens…
Versions 1.26.1 and 1.26.2 of agent-framework on PyPI steal Azure, Azure DevOps, and GitHub Actions credentials when Python starts. The post Microsoft Agent Framework Releases Poisoned With Credential Stealer appeared first on SecurityWeek .
arXiv:2611.20514v1 Announce Type: new Abstract: Replaying a vulnerability's original proof-of-concept after patching tests whether its reported trigger remains reproducible, but does not establish that the underlying security invariant holds on other code paths. We present a ben…
Threat actors have compromised Microsoft's agent-framework package to push a credential stealer, according to reports from Aikido, Chainguard, Endor Labs, OX Security, SafeDep, Socket, StepSecurity, and Google-owned Wiz. The malicious versions, 1.26.1 and 1.26.2, were published …
Our analysis of how attackers used the open-source Cairn AI agent framework to autonomously breach semiconductor, defense and civic targets. The post Attackers Use Autonomous AI to Target Semiconductor, Defense and Civil Society Sectors appeared first on Unit 42 .
OverServe: kỹ thuật resource amplification attack nhắm vào SaaS agents — tenant xấu dùng prompt khai thác quyết định 'khi nào agent tự dừng' để kéo dài execution và đốt tài nguyên model/tool của provider (đặc biệt model subscription-based). Đáng chú ý với ai xây/thẩm định AI agent trong SaaS vì dễ bị lạm dụng chi phí.
Our analysis of how attackers used the open-source Cairn AI agent framework to autonomously breach semiconductor, defense and civic targets. The post Attackers Use Autonomous AI to Target Semiconductor, Defense and Civil Society Sectors appeared first on Unit 42 .
arXiv:2611.19157v1 Announce Type: new Abstract: Grant proposal writing remains a manual, labor-intensive bottleneck: proposals must satisfy rigid, agency-specific templates, and the same intellectual content must be repeatedly re-encoded into incompatible formats across funding …
We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step reasoning. A shared training and deployment pipeline supports interaction with bot…
arXiv:2611.14960v1 Announce Type: new Abstract: Coding agents can solve a task well before they stop working on it. We characterize \emph{termination lag}--the number of steps between an agent's first correct patch and the end of its run--across five models, two agent frameworks…
arXiv:2611.15097v1 Announce Type: new Abstract: Web agents need to use private context without unnecessarily disclosing it. Effective protection must distinguish between requests that may be sent after sanitization and those that must be withheld, while preserving the informatio…
How does a ransomware gang sell a “forced audit”? We break down AuditTeam’s OpsAgent implant, its Rust rewrite, and the extortion model demanding a consulting fee to delete stolen data.