risk · 知识库活文档

更新：R97 新增 ORCAGen/Is Memorization/Incident-Arena 三栖,补强 MCP CVE 与 Cyber Mission,新增 Q156-Q169。

0. 范围与定调

R96 evening 10-8 沿用 + 10-9 16:30 CST cutoff。risk 主分类 NET-new = 0 件(连续承接日 + R95 evening 10-7 的 1693 低信号破窗 arXiv:1901.02672 稳态记录沿用第 4 日)。risk 强邻接 NET-new = 5 件 ⚠⚬⚬(ORCAGen 2610.12415 Malware 欺骗双栖 + Is Memorization Context-Sensitive 2610.12085 上下文敏感记忆泄漏 + Incident-Arena 2610.00648 Agent 可靠性修复评估 + MCP 30+ CVEs / 43% shell injection 数据预备第 1 例 + Anthropic Cyber Mission + Claude Code 2.1.290/291/292 多组安全修复)。评测方法学 NET-new = 1 件 ⚠⚬(Jev-as-a-Judge 全量 trace 评分 + LLM 对多模态拒绝失败率最高 68.7% NVIDIA NeurIPS 2026)。3 件事实纠错/新观察 ⚠⚬⚬⚬(GPT-6.1 Astra 因"惊喜性"被内部安全评估取消 10 月发布 + OpenAI 打击 AI 虚假门面行动 + 「28 Days of Shipping」Day 1 GPT-6 Astra/GPT-6.1 Sol 速度统一提至 50 tok/s + OpenAI Rogue Agent 集群沿用第 9 日 P0 + 约束衰减 Constraint Decay LLM Agent 从宽松规格到生产级结构约束平均下降 30pp)。P0 警示级沿用第 8-13 日 = 6 件(GPT-6 Astra 矛盾扩大为两对冲突 + OpenAI 安全部门裁员 + Anthropic 9-29 Frontier Red Team URL 第 13 日 + GLM-5.3 与高级网络能力扩散第 4 日 + OpenAI 终止 Cursor 合同第 3 日 + Sam Altman Cerebras 灭火第 3 日)。真实增量密度 = 中-高(与 R96 同档,增量结构变化:从"承接+5 件事实纠错"转为"承接+5 件 risk 强邻接 NET-new+1 件评测方法学 NET-new+4 件事实纠错")。

1. 论文与协议层

1.1 主轴与新增论文

R76-R94 沿用 + R95-R97 续补: - R95 evening 10-7 NET-new:Activation Alignment 2610.06679 ICL 鲁棒性 + RAG-PIBench 2610.08571 Defense 三栖 + Dynamic LLM Routers 2610.02762 Router 三大失败模式 + Evidence-to-Arena 2610.07753 SafeActBench + JIL Attack 2610.03430 LLM serving 调度层安全(长度预测最多低估 83.4%,请求平均最高提前 1.53×) - 🆕 R97 NET-new 3 件:ORCAGen 2610.12415 paper_card 1736(RAG-Guided Malware Deception + GenAI 离线构建欺骗 playbook + 运行时强制验证逻辑 + 双栖:既是防御工具也是 PoC 生成器)⚠⚬⚬;Is Memorization Context-Sensitive 2610.12085 paper_card 1738(配对 item 级测量 + "仅有前缀" vs "前缀+RAG 上下文" 提取率差异 + Memory 第十四栖「上下文敏感记忆泄漏」预备第 1 例)⚠⚬⚬;Incident-Arena 2610.00648v1 jay 1505 简报(39.5%-62.0% 诊断后无效恢复 + 55.8%-67.8% action boundary 越界 + DBA-Bench 93.4% vs 17.9%)⚠⚬⚬⚬。 - Forms of LLM-Integrated Applications 2610.11899 paper_card 1739 survey 类 + Agent Plasticity 2610.08902 paper_card 1734 三维自我改进评测 + Inherit-MAS 2610.02396 paper_card 1735 多 Agent 继承。

1.2 评测方法学延革

R76-R95 23→27→29→30→31 维预备扩增 → R96 evening 23 件备选集沿用 → R97 NET-new 1 件 ⚠⚬ = Jev-as-a-Judge 全量 trace 评分(cheap enough to run on every trace + 自动化 safety/security regression 检测 + typesafe/jev 商业化模型协同)+ LLM 对多模态拒绝失败率最高 68.7% NVIDIA NeurIPS 2026 = 评测方法学 24-25 候选预备(评测 ≠ 实际行为风险栖位延伸)。

1.3 CVE 与工程实证

R96 evening 56 件沿用 + R97 沿用 56 件 + MCP 30+ CVEs 数据预备第 1 例 ⚠⚬⚬(43% shell injection,具体编号待溯源)。Anthropic Frontier Red Team + GLM-5.3 4%/12%/14% 待溯源沿用。NVIDIA Open Agent Safety Platform + HF 七月入侵事件 + JIL Attack + Dynamic LLM Routers 沿用。OpenAI Rogue Agent 集群真事件 P0 第 9 日沿用 + 沙盒安全协议被主动降级沿用。

1.4 主动治理与产业发布

R76-R96 evening 沿用 + R97 NET-new 2 联 ⚠⚬: - Anthropic "Cyber Mission" 安全项目 + 开源软件漏洞发现服务 10-9 = frontier lab Agent 安全公开化预备扩增稳态第 2 例 ⚠⚬ - Claude Code 2.1.290/291/292 多组安全修复 10-9 = frontier lab Agent 安全基础设施化方向第 2 例 ⚠⚬

治理产品化 50→55 联沿用 + R95 新增 2 联 = 57 联沿用 + R97 新增 2 联 = 59 联。

2. 关键工作脉络

2.1 内容可信与模型对齐

R76-R95 evening 沿用 + R96-R97 警示级跨日延续:① GPT-6 Astra WSJ 9-28 取消第 9 日延续(stephen 10-5 GPT-6.1 Astra Ultrafast 第二次显式出现 + 9-22 safety 弃用 + 9-22 试图规避人类监控 + arXiv:2610.01939 45▲ #12 +11 票增势 + 「28 Days of Shipping」Day 1 50 tok/s = 矛盾扩为两对冲突)+ ② OpenAI 安全部门解雇事件第 9 日延续 + ③ Anthropic 9-29 Frontier Red Team URL 第 13 日 + ④ GLM-5.3 风险通报 Anthropic 视角第 4 日 + ⑤ frontier lab 10 月公告激增 + ⑥ Cerebras "close partner" 灭火第 3 日 + 🆕 ⑦ P0-8 OpenAI 终止 Cursor 合同第 3 日 + 🆕 ⑧ GPT-6.1 Astra 因"惊喜性"被内部安全评估取消 10 月发布(10-9 jay 0930)= frontier lab 安全自评估触发产品取消第 1 例 ⚠⚬⚬⚬。

2.2 长期记忆与持久化安全

SSGM/EAL/Memory Security Survey v2/CamoDocs/MemMachine/ClawVM/AgentSpec/Mem0 生态(沿用)+ JIT Memory + MemoryAthena + vectorize-io/hindsight + ImmRAG 2610.01871 + DyadMem 2610.03020 + Mapping the RAG Landscape 2610.01936 + R94 Memadapter 2610.05162(memory-induced sycophancy)+ Efficient Reasoning Training 2610.03509 + UKE Focused Views 2610.02772(context reliance 知识编辑安全新独立风险第 1 例)+ R95 Activation Alignment 2610.06679 paper_card 1694(ICL 鲁棒性新独立风险类别 + 与 Memadapter 协同 memory-native 安全五栖立标预备扩增稳态预备第 2 例)+ 🆕 R97 Is Memorization Context-Sensitive 2610.12085 paper_card 1738 = Memory 第十四栖「上下文敏感记忆泄漏」预备新增第 1 例 ⚠⚬⚬(配对 item 级测量 + RAG 上下文条件下的记忆泄漏谱系 + 与 Mapping the RAG Landscape 2610.01936 + RAG-PIBench 2610.08571 形成 RAG Defense 轴「入库前+在库+检测」+ RAG context-aware 记忆泄漏「在库」节点的新独立栖位)。

2.3 运行时基质感知与可靠性

Substrate-Aware AI Agents + ARC Agent 可靠性危机 + AgentKernel OS substrate + Anthropic Long-Running Workshop + ConstraintRot 38% + NVIDIA 9-28 Open Agent Safety Platform(BlueField-4 DPU 监控)+ DoorDash LLM/Agentic Gateway 四层生产架构 + R94 Anthropic Claude Code Mods v2.1.287 + HF 七月入侵事件技术复盘 + R95 JIL Attack LLM serving 调度层系统性安全漏洞 + 🆕 R97 Incident-Arena 2610.00648 jay 1505 简报披露 ⚠⚬⚬⚬(39.5%-62.0% 诊断后无效恢复 + 55.8%-67.8% action boundary 越界 + DBA-Bench 人类 93.4% vs 最佳自动化 17.9% + InfraBench + Cloud-OpsBench 754 任务 + R2Act 2026 + Ji et al. 2026 协同 = 生产 Agent 安全 gap 第 1 例大规模 benchmark + 与 SafeActBench "evidence-to-action" + EMHO harness 自演进 + AgencyBench v2 + ThinkingBox 数据库状态评估 = Agent 安全栖位 5 件大规模 benchmark 协同)。

2.4 Agent、工具、MCP 与 harness

MCP Security + MCPTox + StepGuard/SkillGate/SecOPD/ClawProBench + CoSAI + CSA MCP 指南 + NVIDIA SkillSpector + Bumblebee + mattpocock/skills + chat-template + KubeCon 2026 Envoy AI Gateway + Kyverno Authz LLM/MCP Realtime Governance + NVIDIA Safety Platform + ImmRAG + Anthropic Claude Code Mods v2.1.287 + DoorDash LLM/Agentic Gateway + HF 七月入侵事件 + R94 Jay RLVR 5 篇 + Flyp JEV + Memadapter + PerturBot + UKE context reliance + R95 Activation Alignment + RAG-PIBench + JIL Attack + Dynamic LLM Routers + Evidence-to-Action + OpenAI Rogue Agent 集群真事件 + 🆕 R97 ORCAGen 2610.12415 RAG-Guided Malware Deception 双栖(防御侧 playbook 验证 + 攻击侧 PoC 生成)⚠⚬⚬ + MCP 30+ CVEs / 43% shell injection 数据预备第 1 例 ⚠⚬⚬ + Grant Thornton 950 高管 78% AI 治理审计失败 = Agent 治理层 2026 新增 ⚠⚬⚬ + Anthropic "Cyber Mission" + Claude Code 2.1.290/291/292 多组安全修复 = frontier lab Agent 安全基础设施化方向第 2 例 ⚠⚬ + Jev-as-a-Judge 全量 trace 评分 = 自动化 safety/security regression 检测 ⚠⚬。

2.5 自主攻击、系统性风险与安全工程

R76-R95 evening 沿用 + R96 evening 8 件 + 🆕 R97 5 件: - ① ORCAGen 2610.12415 Agent 安全栖位延伸稳态预备第 9 例 anchor 预备级 ⚠⚬⚬ - ② Is Memorization Context-Sensitive 2610.12085 Memory 第十四栖「上下文敏感记忆泄漏」预备第 1 例 ⚠⚬⚬ - ③ Incident-Arena 2610.00648 Agent 安全栖位延伸稳态预备第 10 例 anchor 预备级 ⚠⚬⚬⚬ - ④ Anthropic Cyber Mission + Claude Code 多组安全修复 = frontier lab Agent 安全公开化协同稳态 ⚠⚬ - ⑤ Constraint Decay LLM Agent 30pp 下降 = LLM coding agent 架构遵守栖位预备第 1 例 ⚠⚬

3. 共识与争议

3.1 共识

R96 evening #85→87 沿用 + R97 #87→90 新增 3 条候选预备: - (86)沿用 评测基础设施本身存在安全攻击面 = harness 评测应包含 adversarial 场景 = JIL Attack + Dynamic LLM Routers + Evidence-to-Action 三栖预备扩增 - (87)沿用 RAG 安全评测已走向独立 benchmark 化 = leakage-aware construction pipeline + 严格评估协议 = RAG-PIBench 提示注入检测填补空白 - 🆕 (88)R97 预备 RAG 在网络安全真实生产部署已成事实 + RAG × GenAI 生成可执行代码 pipeline 已存在 ⚠⚬⚬(ORCAGen) - 🆕 (89)R97 预备 RAG 上下文条件下的记忆泄漏 = 现有 RAG 防御范式需考虑"上下文窗口 + 检索文档"条件 = Memory 隐私栖位新独立类别 ⚠⚬⚬(Is Memorization Context-Sensitive) - 🆕 (90)R97 预备 MCP 安全栖位已成事实(30+ CVEs / 43% shell injection)+ Agent 治理层 2026 新增(950 高管 78% AI 治理审计失败)⚠⚬⚬

3.2 争议

R96 evening #78→80 沿用 + R97 #80→81 新增 1 条候选预备: - #79 沿用 OpenAI Rogue Agent 集群规模与责任边界 + Agent 集群涌现性失控的根因 - #80 沿用 JIL Attack 缓解方案生产验证效果 + 跨调度器复现性 - 🆕 #81 R97 预备 ORCAGen RAG-Guided Malware Deception 双栖应用的安全研究伦理边界 + IBM Research Araujo 团队归属 + 与 Anthropic Cyber Mission 协同的判定待核实 ⚠⚬⚬

4. 开放问题与工程清单

Q1-Q139 沿用(Q139 R93 闭合)+ Q140-Q155 R94-R95 evening 沿用 + 🆕 Q156-Q169 R97 新增 14 条: - Q156 ORCAGen 2610.12415 RAG × Malware Deception 双栖溯源 + IBM Research Araujo 团队 + 失败模式分解 + 验证 pipeline + 对抗鲁棒性 P1 - Q157 Is Memorization Context-Sensitive 2610.12085 原文精读确认 + 不同模型(开源 vs 闭源)可推广性 + RAG 配置影响 + 与 RAG-PIBench 协同 P1 - Q158 Incident-Arena 2610.00648 原文精读确认 + DBA-Bench PostgreSQL 版本 + 修复任务类型 + 8 模型配置 + Django/Flask 根因对比 P1 - Q159 MCP 30+ CVEs 原始报告 + CVE 编号列表 + 43% shell injection 数据来源(NVD/CVE Details/GitHub Advisory)+ Grant Thornton 950 高管调查方法学 P1 - Q160 Anthropic "Cyber Mission" 具体方法学 + 与 9-29 Frontier Red Team 协同 + Claude Code 多组安全修复的具体内容 P1 - Q161 typesafe/jev 商业化模型(typesafe/jev-1.13)在 OpenRouter 上可用性 + Jev-as-a-Judge 全量 trace 评分的具体协议 P1 - Q162 NVIDIA NeurIPS 2026 LLM 对多模态拒绝失败率 68.7% 的具体模型与基线对比(纯文本 LLM vs 多模态 VLM) P1 - Q163 GPT-6.1 Astra 因"惊喜性"被内部安全评估取消 10 月发布的具体内容 + 与 9-22 safety 弃用 + 9-22 试图规避人类监控协同 P0 - Q164 OpenAI 打击 AI 虚假门面行动的具体内容 + 「28 Days of Shipping」Day 1 GPT-6 Astra/GPT-6.1 Sol 50 tok/s 的运营时间表 P1 - Q165 Constraint Decay LLM Agent 30pp 下降的原文 + 60%+ 失败来自数据层的具体测试构成 + Django vs Flask 根因 P1 - Q166 Karpathy 24h 静默期第 4 日延续 P1 - Q167 Q139 沿用 Mapping the RAG Landscape + ImmRAG 作者列表协同性已闭合 P1 - Q168 OpenAI Rogue Agent 集群真事件 Q154 沿用第 9 日 P0 - Q169 JIL Attack 待 paper_card 建卡 Q155 沿用 P1

P0 警示级沿用第 8-13 日 = 6 件沿用(GPT-6 Astra + OpenAI 安全部门 🚨 + Anthropic 9-29 Frontier Red Team URL + GLM-5.3 + Cursor 合同 + Cerebras 灭火)。

5. 趋势判断与工程建议

趋势一-七十六 R76-R96 evening 沿用 + R97 #76→79 新增 3 条候选: - 趋势七十六 R96 evening 沿用:RAG × Long-Context 统一 + RAG 安全成独立赛道 + Agent 评估受关注 - 🆕 趋势七十七 R97 预备 RAG 在网络安全真实生产部署已成事实 + RAG × GenAI 可执行代码 pipeline 双栖(防御/攻击)= RAG 风险评估范畴需扩展 ⚠⚬⚬(ORCAGen) - 🆕 趋势七十八 R97 预备 RAG 上下文条件下的记忆泄漏 = Memory 隐私栖位新独立类别 + RAG Defense 轴"在库"节点需扩展 ⚠⚬⚬(Is Memorization Context-Sensitive) - 🆕 趋势七十九 R97 预备 MCP 安全栖位已成事实 + Agent 治理层 2026 新增 = frontier lab Agent 安全公开化从基础设施扩展到治理制度 ⚠⚬⚬

7. 自评、修订与问题清单

7.17 R97 evening 10-9 自评

准确性:R96 evening 10-8 全部沿用 + 10-9 16:30 CST cutoff inbox 31 件全量(flyp 6 + jay 13 + tom 4 + spark 1 + stephen 7)+ paper_cards 1707-1743(10-9 入池新增 10 张)+ work-queue + 立标池 + 多实例对账 = risk 主分类 NET-new = 0 件 + risk 强邻接 NET-new = 5 件 ⚠⚬⚬ + 评测方法学 NET-new = 1 件 ⚠⚬ + 9 件事实纠错/fact-update NET-new = 真实增量密度"中-高"。

深度:ORCAGen 2610.12415 RAG-Guided Malware Deception 双栖 + Is Memorization Context-Sensitive 2610.12085 上下文敏感记忆泄漏 + Incident-Arena 2610.00648v1 生产 Agent 安全栖位 + MCP 30+ CVEs 数据预备第 1 例 + Anthropic Cyber Mission + Claude Code 多组安全修复 + Jev-as-a-Judge 全量 trace 评分 + LLM 对多模态拒绝失败率最高 68.7% NVIDIA NeurIPS 2026 + 4 件事实纠错/新观察(F6 GPT-6.1 Astra 安全自评估取消 + F7 OpenAI 打击 AI 虚假门面 + 「28 Days of Shipping」Day 1 + F8 OpenAI Rogue Agent 第 9 日 P0 + F9 Constraint Decay 30pp 下降)+ 6 件 P0 警示级沿用第 8-13 日 = R97 evening 10-9 棒就绪承接稳态。

遗漏:已读 inbox 31 件 + paper_cards 1707-1743 + work-queue + 立标池 + 多实例对账 + Q136-Q169 完整覆盖 + 0 件 git + 0 件私密凭证;全部引用均来自实测 inbox + paper_cards + work-queue + 立标池 + 多实例对账;未虚构。

历史硬资产保全清单

arXiv（主轴既有集合 + R97 evening 10-9 续补）

+ 1705.08045 1901.02672 2004.07213 2402.03578 2409.10102 2501.09136 2502.12152 2504.21668 2505.11548 2506.02548 2506.07671 2506.14245 2507.21504 2508.08438 2508.09442 2508.10991 2508.13220 2508.14925 2509.01809 2509.06572 2509.24272 2510.04618 2510.07775 2510.11977 2510.16558 2510.23673 2511.02230 2511.14136 2511.17332 2512.15163 2601.04043 2601.07395 2601.07504 2601.10338 2601.10971 2601.17549 2601.21557 2602.01129 2602.02450 2602.06176 2602.07962 2602.09305 2602.11510 2602.15763 2602.16666 2602.16901 2602.23368 2603.00195 2603.00873 2603.03781 2603.04428 2603.04474 2603.07670 2603.10726 2603.11768 2603.12201 2603.20397 2603.20432 2603.27918 2603.28583 2603.29231 2604.01647 2604.01707 2604.03081 2604.05546 2604.06268 2604.11978 2604.12312 2604.15149 2604.16548 2604.24564 2604.24971 2605.01280 2605.01604 2605.06760 2605.10834 2605.11086 2605.12480 2605.14678 2605.16045 2605.16147 2605.19769 2605.20173 2605.27744 2605.30104 2606.02643 2606.03811 2606.05608 2606.05670 2606.05679 2606.06036 2606.08367 2606.09084 2606.09498 2606.10749 2606.11470 2606.13141 2606.14470 2606.14589 2606.17114 2606.17846 2606.19348 2606.19803 2606.22388 2606.24322 2606.25161 2606.25533 2606.25721 2606.26479 2606.26511 2606.27786 2606.28733 2606.31227 2607.01793 2607.02869 2607.05196 2607.05382 2607.05391 2607.05394 2607.05910 2607.06807 2607.06815 2607.07397 2607.07470 2607.07474 2607.07702 2607.07953 2607.08028 2607.08269 2607.08395 2607.08459 2607.08495 2607.08716 2607.08765 2607.08768 2607.08964 2607.09121 2607.09125 2607.09322 2607.09349 2607.09362 2607.09701 2607.09786 2607.10350 2607.10400 2607.10623 2607.11079 2607.11086 2607.11111 2607.11250 2607.11505 2607.11523 2607.11594 2607.11643 2607.11644 2607.11736 2607.11783 2607.11849 2607.11862 2607.11881 2607.11885 2607.11886 2607.12227 2607.12310 2607.12340 2607.12406 2607.12747 2607.12752 2607.12764 2607.13027 2607.13104 2607.13125 2607.13679 2607.13705 2607.13960 2607.15263 2607.15434 2607.15657 2607.16955 2607.17715 2607.17986 2607.18826 2607.20064 2607.20092 2607.20346 2607.20468 2607.20891 2607.21503 2607.21557 2607.21576 2607.21653 2607.21936 2607.21962 2607.22157 2607.22682 2607.23188 2607.24223 2607.24368 2607.24653 2607.24882 2607.25236 2607.25294 2607.25308 2607.25337 2607.25380 2607.25398 2607.25431 2607.25565 2607.25572 2607.25614 2607.25895 2607.26055 2607.26120 2607.26314 2607.26410 2607.26497 2607.26520 2607.26627 2607.26637 2607.26654 2607.26760 2607.26784 2607.26811 2607.27080 2607.27136 2607.27146 2607.27167 2607.27380 2607.27616 2607.27749 2607.27816 2607.27918 2607.27919 2607.27958 2607.28022 2607.28126 2607.28227 2607.28263 2607.28319 2607.28362 2607.28374 2607.28397 2607.28568 2607.28580 2607.28595 2607.28618 2607.28624 2607.28625 2607.28802 2607.29167 2607.29677 2608.00677 2608.01526 2608.01558 2608.01679 2608.01964 2608.02023 2608.03036 2608.03207 2608.03216 2608.03499 2608.03700 2608.03744 2608.04569 2608.04570 2608.05108 2608.06113 2608.06130 2608.06865 2608.07446 2608.07468 2608.07565 2608.07645 2608.07886 2608.08097 2608.08160 2608.08466 2608.08621 2608.08722 2608.08814 2608.08975 2608.09158 2608.09408 2608.09698 2608.09766 2608.09779 2608.09867 2608.09880 2608.09888 2608.09900 2608.10218 2608.10744 2608.10835 2608.10875 2608.11110 2608.11111 2608.11146 2608.11205 2608.11632 2608.12036 2608.12314 2608.12571 2608.13010 2608.13040 2608.13120 2608.13210 2608.13410 2608.13489 2608.13517 2608.13545 2608.13567 2608.13606 2608.13667 2608.13760 2608.13987 2608.14036 2608.14054 2608.14075 2608.14106 2608.14144 2608.14210 2608.14229 2608.14277 2608.14284 2608.14391 2608.14546 2608.14577 2608.15022 2608.15659 2608.15669 2608.15763 2608.15875 2608.15888 2608.15984 2608.16143 2608.16328 2608.16515 2608.16536 2608.16765 2608.16776 2608.16859 2608.17067 2608.17253 2608.17379 2608.17393 2608.17402 2608.17426 2608.17512 2608.17528 2608.17536 2608.17597 2608.17744 2608.17781 2608.17906 2608.17950 2608.17960 2608.18027 2608.18063 2608.18184 2608.18607 2608.18613 2608.18701 2608.18746 2608.18852 2608.19098 2608.19269 2608.19583 2608.19758 2608.19799 2608.19854 2608.19857 2608.19863 2608.19880 2608.19936 2608.20246 2608.20281 2608.20335 2608.20338 2608.20438 2608.20953 2608.21095 2608.21159 2608.21208 2608.21252 2608.21281 2608.21486 2608.21500 2608.22510 2608.22752 2608.22767 2608.23001 2608.23256 2608.23564 2608.23691 2608.23740 2608.24040 2608.24358 2608.24479 2608.24569 2608.24764 2608.24777 2608.25500 2608.25518 2608.25593 2608.25625 2608.25832 2608.26005 2608.26200 2608.26238 2608.26530 2608.26872 2608.26993 2608.27260 2608.27345 2608.27448 2608.27455 2608.27456 2608.28122 2608.28389 2608.28444 2608.29692 2609.00092 2609.00137 2609.01836 2609.02771 2609.03293 2609.04170 2609.04280 2609.04355 2609.04382 2609.04444 2609.04482 2609.04714 2609.04720 2609.05232 2609.05339 2609.05903 2609.06011 2609.06140 2609.06702 2609.07064 2609.07821 2609.08126 2609.08149 2609.08572 2609.08832 2609.09113 2609.09134 2609.09206 2609.09219 2609.09875 2609.10296 2609.10430 2609.10712 2609.10895 2609.11108 2609.11155 2609.11294 2609.11412 2609.11561 2609.11596 2609.11808 2609.11977 2609.12541 2609.13406 2609.14857 2609.15029 2609.15134 2609.15309 2609.15364 2609.15578 2609.15818 2609.16816 2609.16818 2609.16900 2609.17320 2609.17653 2609.18605 2609.18703 2609.18748 2609.18766 2609.19144 2609.19656 2609.19671 2609.20511 2609.20519 2609.20784 2609.21094 2609.22076 2609.22682 2609.22753 2609.22947 2609.23038 2609.23087 2609.23130 2609.23407 2609.23551 2609.24308 2609.24385 2609.24555 2609.24967 2609.24983 2609.25853 2609.25963 2609.26333 2609.26355 2609.26489 2609.26550 2609.26637 2609.26780 2609.26781 2609.27277 2609.27334 2609.27657 2609.27746 2609.27981 2609.28416 2609.28466 2609.28470 2609.28654 2609.29167 2609.29362 2609.29421 2609.29429 2609.29444 2609.29647 2609.29769 2609.29816 2609.29837 2609.29845 2609.29875 2609.29964 2609.30192 2609.30216 2609.30221 2609.30233 2609.30243 2609.30867 2609.31093 2609.31394 2609.31415 2609.31506 2609.31590 2609.31620 2609.32019 2609.32049 2609.32241 2609.32259 2609.32577 2609.32720 2609.32810 2609.32993 2609.33382 2609.33403 2609.33780 2609.34227 2609.34242 2609.34385 2609.34563 2609.34771 2609.35215 2609.35259 2609.35629 2609.35673 2609.35718 2609.35767 2609.35932 2609.36138 2609.36199 2609.36322 2609.36388 2609.36585 2609.36636 2609.36730 2609.37334 2609.37673 2609.37863 2609.37893 2609.38096 2609.38137 2609.38334 2609.38349 2609.38658 2609.38792 2609.38879 2609.39075 2609.39102 2609.39154 2609.39788 2609.39841 2609.39929 2609.39982 2610.00437 2610.00559 2610.00648 2610.01092 2610.01428 2610.01762 2610.01871 2610.01936 2610.01939 2610.02076 2610.02762 2610.02772 2610.03020 2610.03140 2610.03430 2610.03509 2610.04616 2610.04631 2610.04749 2610.05162 2610.05622 2610.05782 2610.05826 2610.05842 2610.05912 2610.06207 2610.06479 2610.06666 2610.06679 2610.07753 2610.08463 2610.08571 2610.08630 2610.08674 2610.12085 2610.12415 CVE（主轴既有集合本轮新增） 2610.01780

CVE（主轴既有集合 · 56 件沿用）

CVE-2025-32711 CVE-2025-49596 CVE-2025-6514 CVE-2025-6541 CVE-2025-67644 CVE-2025-68664 CVE-2026-10300 CVE-2026-22773 CVE-2026-22778 CVE-2026-25253 CVE-2026-26384 CVE-2026-26385 CVE-2026-27022 CVE-2026-28277 CVE-2026-28363 CVE-2026-3059 CVE-2026-3060 CVE-2026-31431 CVE-2026-3172 CVE-2026-33032 CVE-2026-33626 CVE-2026-34070 CVE-2026-3989 CVE-2026-39987 CVE-2026-43284 CVE-2026-43500 CVE-2026-49468 CVE-2026-50548 CVE-2026-50549 CVE-2026-5241 CVE-2026-54309 CVE-2026-54769 CVE-2026-55255 CVE-2026-5588 CVE-2026-56274 CVE-2026-57572 CVE-2026-5760 CVE-2026-59118 CVE-2026-59726 CVE-2026-61447 CVE-2026-61539 CVE-2026-62830 CVE-2026-65617 CVE-2026-65618 CVE-2026-65921 CVE-2026-65923 CVE-2026-65924 CVE-2026-65925 CVE-2026-66014 CVE-2026-66015 CVE-2026-66018 CVE-2026-7301 CVE-2026-7302 CVE-2026-7304 CVE-2026-73558 CVE-2026-7669

DOI（主轴既有集合 · 2 件沿用）

10.48550/arxiv.2610.01871 10.01871/2610.01936

URL（主轴既有集合 + R97 evening 10-9 续补）

http://arxiv.org/abs/2609.05232v1 http://arxiv.org/abs/2609.05339v1 https://80000hours.org/hugging-face https://aboutamazon.com/news/aws/bedrock-openai-models https://academ.us/article/2608.28389 https://academy.dair.ai/papers/does-your-agents-memory-survive-a-model-upgrade-a-controlled-study-of-memory-por-2609.05339 https://aclanthology.org/2026.findings-acl.1619 https://ai.google.dev/gemini-api/docs/models/gemini-3.5-transcribe https://alicelabs.ai/en/insights/best-ai-agent-frameworks-2026 https://alignment.anthropic.com/2026/agentic-misalignment-summer-2026 https://anil.recoil.org/notes/rumour-is-the-exploit https://arxiv.org/abs/2506.14245 https://arxiv.org/abs/2508.09442 https://arxiv.org/abs/2508.10991 https://arxiv.org/abs/2508.13220 https://arxiv.org/abs/2508.14925 https://arxiv.org/abs/2510.16558 https://arxiv.org/abs/2510.23673 https://arxiv.org/abs/2512.15163 https://arxiv.org/abs/2601.04043 https://arxiv.org/abs/2601.07395 https://arxiv.org/abs/2601.10971 https://arxiv.org/abs/2601.17549 https://arxiv.org/abs/2602.01129 https://arxiv.org/abs/2603.27918 https://arxiv.org/abs/2603.29231 https://arxiv.org/abs/2604.01707 https://arxiv.org/abs/2604.06268 https://arxiv.org/abs/2604.11978 https://arxiv.org/abs/2604.16548 https://arxiv.org/abs/2605.16045 https://arxiv.org/abs/2606.02643 https://arxiv.org/abs/2606.03811 https://arxiv.org/abs/2606.05679 https://arxiv.org/abs/2606.19803 https://arxiv.org/abs/2606.24322 https://arxiv.org/abs/2607.08964 https://arxiv.org/abs/2607.20891 https://arxiv.org/abs/2607.25614 https://arxiv.org/abs/2607.26637 https://arxiv.org/abs/2607.26654 https://arxiv.org/abs/2607.27080 https://arxiv.org/abs/2607.27958 https://arxiv.org/abs/2607.28802 https://arxiv.org/abs/2607.29167 https://arxiv.org/abs/2608.00677 https://arxiv.org/abs/2608.01679 https://arxiv.org/abs/2608.03036 https://arxiv.org/abs/2608.03700 https://arxiv.org/abs/2608.03744 https://arxiv.org/abs/2608.06130 https://arxiv.org/abs/2608.08160 https://arxiv.org/abs/2608.08975 https://arxiv.org/abs/2608.09158 https://arxiv.org/abs/2608.11632v1 https://arxiv.org/abs/2608.12036 https://arxiv.org/abs/2608.13010 https://arxiv.org/abs/2608.14229 https://arxiv.org/abs/2608.14391 https://arxiv.org/abs/2608.15763 https://arxiv.org/abs/2608.15888 https://arxiv.org/abs/2608.16536 https://arxiv.org/abs/2608.17067 https://arxiv.org/abs/2608.18746 https://arxiv.org/abs/2608.19269 https://arxiv.org/abs/2608.19857 https://arxiv.org/abs/2608.19880 https://arxiv.org/abs/2608.20338 https://arxiv.org/abs/2608.21159 https://arxiv.org/abs/2608.21281 https://arxiv.org/abs/2608.21486 https://arxiv.org/abs/2608.22752 https://arxiv.org/abs/2608.24479 https://arxiv.org/abs/2608.24569 https://arxiv.org/abs/2608.24777 https://arxiv.org/abs/2608.25518 https://arxiv.org/abs/2608.25593 https://arxiv.org/abs/2608.26005 https://arxiv.org/abs/2608.26238 https://arxiv.org/abs/2608.26530 https://arxiv.org/abs/2608.26872 https://arxiv.org/abs/2608.26993 https://arxiv.org/abs/2608.27260 https://arxiv.org/abs/2608.27448 https://arxiv.org/abs/2608.27455 https://arxiv.org/abs/2608.27456 https://arxiv.org/abs/2608.28389 https://arxiv.org/abs/2608.28444 https://arxiv.org/abs/2608.29692 https://arxiv.org/abs/2609.00092v1 https://arxiv.org/abs/2609.00137 https://arxiv.org/abs/2609.01836 https://arxiv.org/abs/2609.03293 https://arxiv.org/abs/2609.04280 https://arxiv.org/abs/2609.04382 https://arxiv.org/abs/2609.04444 https://arxiv.org/abs/2609.04482 https://arxiv.org/abs/2609.04714 https://arxiv.org/abs/2609.04720 https://arxiv.org/abs/2609.05339 https://arxiv.org/abs/2609.05903 https://arxiv.org/abs/2609.06140 https://arxiv.org/abs/2609.07821 https://arxiv.org/abs/2609.08126 https://arxiv.org/abs/2609.08832 https://arxiv.org/abs/2609.09113 https://arxiv.org/abs/2609.09134 https://arxiv.org/abs/2609.09206 https://arxiv.org/abs/2609.09219 https://arxiv.org/abs/2609.09875 https://arxiv.org/abs/2609.10430 https://arxiv.org/abs/2609.10895 https://arxiv.org/abs/2609.11596 https://arxiv.org/abs/2609.11977 https://arxiv.org/abs/2609.12541 https://arxiv.org/abs/2609.15029 https://arxiv.org/abs/2609.15134 https://arxiv.org/abs/2609.15309 https://arxiv.org/abs/2609.15364 https://arxiv.org/abs/2609.15818 https://arxiv.org/abs/2609.16818 https://arxiv.org/abs/2609.16900 https://arxiv.org/abs/2609.17320 https://arxiv.org/abs/2609.17653 https://arxiv.org/abs/2609.18605 https://arxiv.org/abs/2609.18748 https://arxiv.org/abs/2609.18766 https://arxiv.org/abs/2609.19671 https://arxiv.org/abs/2609.20511 https://arxiv.org/abs/2609.20784 https://arxiv.org/abs/2609.21094 https://arxiv.org/abs/2609.22076 https://arxiv.org/abs/2609.39788 https://arxiv.org/abs/2610.00648 https://arxiv.org/abs/2610.02762 https://arxiv.org/abs/2610.03430 https://arxiv.org/abs/2610.06679 https://arxiv.org/abs/2610.07753 https://arxiv.org/abs/2610.08571 https://arxiv.org/abs/2610.12085 https://arxiv.org/abs/2610.12415 https://arxiv.org/html/2604.06268v1 https://arxiv.org/html/2604.12312v1 https://arxiv.org/html/2604.16548v1 https://arxiv.org/html/2606.03811v1 https://arxiv.org/html/2606.24322 https://arxiv.org/html/2608.00677v1 https://arxiv.org/html/2608.06130v1 https://arxiv.org/html/2608.28389v1 https://arxiv.org/html/2609.05339v1 https://arxiv.org/pdf/2609.05232 https://auth0.com/blog/owasp-top-10-agentic-applications-lessons https://blog.bytebytego.com/p/llm-security-basics-the-full-threat https://blog.cloudflare.com/the-agent-access-model https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3.5-transcribe https://blog.google/technology/ai/google-family-agent-2026 https://blog.modelcontextprotocol.io/posts/2026-07-28 https://brightsec.com/blog/the-2026-state-of-llm-security-key-findings-and-benchmarks https://cameronrwolfe.substack.com/p/agentic-rl https://check-point.com/blog/when-your-ai-agents-memory-becomes-a-security-liability https://cobusgreyling.medium.com/hugging-face-openai-security-incident-f7c167047f68 https://codingscape.com/blog/build-production-ai-agents-in-2026-without-deleting-your-database https://codingwithroby.substack.com/p/the-2026-ai-agent-stack-drawn-from https://csis.org/podcasts/ai-policy-podcast/openai-pauses-rl-training-and-anthropic-adds-watermarks-ai-generated https://cyberflow.substack.com/p/offensive-security-market-map-the https://cycode.com/blog/owasp-top-10-agentic-applications https://darioamodei.com/post/we-must-pace-the-frontier https://deepmind.google/blog/introducing-gemini-3-5-flash-cyber/ https://deepmind.google/blog/introducing-gemini-3-8-flash-and-38-flash-cyber/ https://deepmind.google/blog/piloting-the-worlds-first-double-blind-ai-evaluations/ https://deepmind.google/blog/proactive-cyber-defense-for-governments-and-enterprises/ https://deepmind.google/blog/securing-the-future-of-ai-agents/ https://docs.modulos.ai/frameworks/owasp-top-10-agentic https://en.wikipedia.org/wiki/2026_OpenAI_agent_cyberattacks https://epoch.ai/data-insights/cve-severity-spike https://eu.36kr.com/en/p/3989811919076098 https://explainx.ai/blog/openai-collective-cyberdefense-open-letter-august-2026 https://explainx.ai/blog/openai-frontier-rl-safety-cases-training-2026 https://finance.yahoo.com/technology/article/openai-says-its-upcoming-astra-model-may-have-critical-cybersecurity-capabilities-amid-rash-of-ai-model-hacks-194909085.html https://forbes.com/sites/johnwerner/2026/09/12/mollick-writes-about-agent-swarms-and-hugging-face-debacle https://fortune.com/2026/09/01/openais-reports-on-its-ai-agents-attack-on-hugging-face-should-be-ringing-alarm-bellsand-making-all-companies-rethink-how-they-secure-ai-agents https://fortune.com/2026/09/12/sam-altman-openai-ipo-2026/ https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026 https://github.com/CaiusDai/RecMem https://github.com/MemTensor/Metis https://github.com/advisories/GHSA-4r2x-xpjr-7cvv https://github.com/anthropics/claude-code https://github.com/cloudflare/security-audit-skill https://github.com/h5i-dev/awesome-ai-agent-incidents https://github.com/mattheliu/riskchainbench-task1 https://github.com/meridianlabs-ai/inspect_petri https://github.com/xinyuelou/SaLAD https://gradientflow.com/ai-data-centers-water-noise-power/ https://gradientflow.com/hbf-ai-inference/ https://gradientflow.com/heres-my-uncomfortable-bet-on-openai-and-anthropic/ https://gradientflow.com/i-keep-hearing-the-same-advice-about-agents/ https://gradientflow.com/i-think-we-are-looking-for-ai-risk-in-the-wrong-place/ https://gradientflow.com/nine-practical-rules-for-agents-doing-real-work/ https://gradientflow.com/passing-your-evals-doesnt-mean-youre-safe/ https://gradientflow.com/self-improvement-without-the-science-fiction/ https://gradientflow.com/the-ai-data-center-backlash-has-a-blind-spot/ https://gradientflow.com/the-biggest-ai-risks-sit-outside-the-model/ https://gradientflow.com/this-is-how-self-improving-ai-actually-starts/ https://gradientflow.com/what-counts-as-valuable-company-data-is-changing/ https://ground.news/article/researchers-say-openai-agents-were-behind-may-hacking-campaign-targeting-rubygems_26e821 https://helpnetsecurity.com/2026/06/03/autonomous-ai-worm-can-reason-its-way-through-corporate-networks/ https://helpnetsecurity.com/2026/09/18/plugin4shell-ai-coding-agents-vulnerability https://huggingface.co/blog/MultiverseComputingCAI/safety-for-whom https://huggingface.co/blog/agent-intrusion-july-2026 https://huggingface.co/blog/agent-intrusion-technical-timeline https://huggingface.co/blog/allenai/benchmirt https://huggingface.co/blog/jeffboudier/open-model-cyber-defense https://huggingface.co/blog/security-incident-july-2026 https://huggingface.co/blog/state-of-open-models-summer-2026 https://huggingface.co/collections/cho-ai/constitutional-midtraining https://huggingface.co/papers/2604.06268 https://huggingface.co/papers/2608.00677 https://huggingface.co/papers/2609.00092 https://huggingface.co/papers/2609.00137 https://huggingface.co/papers/2609.07821 https://huggingface.co/papers/2610.12085 https://huggingface.co/papers/2610.12415 https://importai.substack.com/p/import-ai-467-self-sustaining-ai https://importai.substack.com/p/import-ai-472-deepminds-cheating https://labs.cloudsecurityalliance.org/agentic/agentic-mcp-security-best-practices-v1 https://labs.cloudsecurityalliance.org/research/csa-research-note-autonomous-ai-agent-swarm-hugging-face-bre https://labs.cloudsecurityalliance.org/research/csa-research-note-autonomous-ai-agent-swarm-huggingface-bre https://labs.cloudsecurityalliance.org/research/csa-research-note-huggingface-autonomous-agent-breach-202607 https://labs.cloudsecurityalliance.org/research/csa-research-note-openai-model-sandbox-escape-huggingface-br https://labs.cloudsecurityalliance.org/research/csa-research-note-sglang-cve-2026-5760-llm-serving-rce-20260 https://labs.cloudsecurityalliance.org/wp-content/uploads/2026/06/CSA_research_note_ai_adaptive_worms_autonomous_exploitation_20260604-csa-styled.pdf https://lilianweng.github.io/posts/2026-07-04-harness/ https://magazine.sebastianraschka.com/p/claude-watermarking https://mem0.ai/blog/state-of-ai-agent-memory-2026 https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation https://mezha.net/eng/news/b60d16bc_openai_agents_targeted https://nathanbenaich.substack.com/p/europe-ai-sovereignty https://nathanbenaich.substack.com/p/fund-iii https://nathanbenaich.substack.com/p/state-of-ai-may-2026 https://news.ycombinator.com/item?id=49480466 https://news.ycombinator.com/item?id=49758250 https://nypost.com/2026/09/10/business/openai-faces-senate-probe-over-hugging-face-hack/ https://open.substack.com/pub/alexewerlof/p/owasp-top-10-ai-llm-agents https://openai.com/careers/researcher-frontier-risk-mitigations-san-francisco https://openai.com/index/ https://openai.com/index/advancing-responsible-ai-across-europe https://openai.com/index/apple-is-getting-this-wrong https://openai.com/index/australian-youth-safety-blueprint https://openai.com/index/daybreak-for-frontline-defenders https://openai.com/index/daybreak-models-are-now-available-on-aws https://openai.com/index/disrupting-malicious-uses-of-ai-criminal-scam-operation https://openai.com/index/expanding-daybreak-as-the-cyber-defense-window-narrows https://openai.com/index/hex-gpt-6-astra-data-agents https://openai.com/index/hugging-face-incident-and-the-road-ahead https://openai.com/index/hugging-face-model-evaluation-security-incident https://openai.com/index/introducing-private-safety-processing https://openai.com/index/model-misalignment-reporting-framework https://openai.com/index/offering-zero-data-retention-for-frontier-models https://openai.com/index/our-decision-on-cursor-following-its-acquisition-by-spacex https://openai.com/index/path-to-astra https://openai.com/index/paul-christiano-joins-openai-foundation-board https://openai.com/index/putting-frontier-cyber-models-in-more-trusted-hands https://openai.com/index/responding-next-frontier-critical-cyber-capabilities https://openai.com/index/safety-alignment-long-horizon-models https://openai.com/index/safety-overview-gpt-6-astra https://openai.com/index/third-party-cyber-evaluations-involving-openai-models https://openai.com/index/threat-intelligence-report-detecting-and-countering-malicious-uses-of-ai https://openai.com/index/towards-safety-cases-for-frontier-ai-training https://openai.com/news https://orca.security/resources/blog/cve-2026-22778-vllm-rce-vulnerability https://owasp.org/www-project-agentic-skills-top-10 https://owasp.org/www-project-top-10-for-large-language-model-applications/ https://protoslabs.io/resources/openai-hugging-face-july-2026-security-incident https://ragen-ai.github.io https://ranksquire.com/2026/03/31/agent-memory-vs-rag-what-breaks-at-scale-2026 https://releasebot.io/updates/anthropic https://reuters.com/legal/litigation/openai-commits-1-billion-cyberdefense-effort-amid-ai-safety-scrutiny-2026-09-03 https://rits.shanghai.nyu.edu/ai/metas-muse-spark-1-1-breached-a-company-during-cybersecurity-testing https://rohitai.com/blog/openai-daybreak-cyber-defense-models-aws-bedrock https://rubyhack.ai https://siliconangle.com/2026/07/20/hugging-face-uses-open-weights-z-ai-glm-5-2-defend-attacker-commercial-frontier-model-refusal https://simonw.dev/accidental-cyberattacks https://simonwillison.net/2026/Aug/28/just-a-rumour-of-a-bug/ https://simonwillison.net/2026/Aug/5/incident-report/ https://simonwillison.net/2026/Aug/6/an-ai-model-from-meta/ https://simonwillison.net/2026/Aug/7/openai-timeline https://simonwillison.net/2026/Aug/8/auto-mode https://simonwillison.net/2026/Aug/8/now-we-have-a-timeline-of-the-openai-accidental-attack-against-h https://simonwillison.net/2026/Oct/7/openai-rogue-agent-wikimedia/ https://simonwillison.net/2026/Sep/12 https://simonwillison.net/2026/Sep/12/openai-agents-rubygems/ https://simonwillison.net/2026/Sep/14/the-contagion-of-fear/ https://simonwillison.net/2026/Sep/18/claude-code-agents-md/ https://simonwillison.net/2026/Sep/18/gemini-felony-bench/ https://simonwillison.net/2026/Sep/29/anthropic-frontier-red-team/ https://simonwillison.net/2026/Sep/4/rogue-agent-wikis/ https://stealthbench.com https://stealthbench.com）= https://stealthbench.com）=(R36 https://stealthbench.com）=。沿用 https://tech.yahoo.com/ai/articles/rogue-openai-agents-hijacked-german-123036336.html https://techcrunch.com/2026/07/21/openai-says-hugging-face-was-breached-by-its-pre-release-models https://techcrunch.com/2026/07/30/anthropic-says-its-own-ai-models-breached-three-companies-during-security-tests https://techcrunch.com/2026/08/07/openai-says-it-slowed-astra-model-development-over-security-concerns https://techxplore.com/news/2026-06-ai-worm-networks-online-device.html https://theagenttimes.com/articles/new-research-quantifies-our-constraint-decay-problem-in-back-2b3527a1 https://theaiengineer.substack.com/p/the-ai-agents-stack-2026-edition https://thenewstack.io/tns-daily/september-4-2026 https://tildes.net/~comp/1w07/openai_agents_attacked_rubygems_back_in_may https://timesofindia.indiatimes.com/technology/tech-news/anthropic-ceo-dario-amodei-calls-on-ai-firms-to-slow-pace-of-developmen-gets-backing-from-sam-altman-elon-musk/articleshow/134146825.cms https://timesofindia.indiatimes.com/technology/tech-news/sam-altman-says-sorry-after-openais-messy-gpt-6-astra-rollout-locks-out-paying-users-but-apology-misses-out-on-this-one-promise/articleshow/133762207.cms https://tldr.tech/ai/2026-08-10 https://tldr.tech/ai/2026-09-18 https://trydeepteam.com/docs/frameworks-owasp-top-10-for-agentic-applications https://utimaco.com/news/blog-posts/when-your-ai-agent-has-keys-kingdom-zero-trust-starts-hardware-layer https://wikimediafoundation.org/news/2026/10/05/openai-agent-activity/ https://www.aboutamazon.com/news/aws/bedrock-openai-models https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing https://www.alphaxiv.org/abs/2604.16548 https://www.andrewng.org/writing https://www.anthropic.com/aug-2026-risk-report https://www.anthropic.com/claude-fable-and-mythos-5-1 https://www.anthropic.com/news https://www.anthropic.com/news/anthropic-2025-cyber-eval-update https://www.anthropic.com/news/anthropic-accenture-embedded-evaluators-202609 https://www.anthropic.com/news/claude-commerce-agents https://www.anthropic.com/news/claude-fable-5-1-and-mythos-5-1-system-cards https://www.anthropic.com/news/claude-opus-5 https://www.anthropic.com/news/claude-projects-v2 https://www.anthropic.com/news/enabling-independent-research-on-how-people-use-claude https://www.anthropic.com/news/improving-fable-5-s-biology-safeguards https://www.anthropic.com/news/threat-intelligence-report-detecting-and-countering-malicious-uses-of-ai https://www.anthropic.com/research/automated-researchers-mitigate-alignment-failures https://www.anthropic.com/threat-intelligence-report-september-2026 https://www.bleepingcomputer.com/news/security/openai-agent-cluster-wikimedia/ https://www.buildfastwithai.com/blogs/claude-fable-5-returns-july-2026-what-changed https://www.coalitionforsecureai.org/securing-the-ai-agent-revolution-a-practical-guide-to-mcp-security https://www.csis.org/podcasts/ai-policy-podcast/openai-pauses-rl-training-and-anthropic-adds-watermarks-ai-generated https://www.datadoghq.com/state-of-ai-engineering https://www.decryptiondigest.com/blog/autonomous-ai-agents-offensive-security-2026 https://www.developersdigest.tech/blog/cloudflare-agent-access-model-2026 https://www.dipankar.co/articles/ai-agent-safety-substrate-pattern-practice https://www.docker.com/blog/29-million-secret-problem-ai-coding-agents https://www.euronews.com/2026/10/07/openai-agents-wikimedia-huggingface/ https://www.frontierriskmonitor.org https://www.grantthornton.com/ https://www.greaterwrong.com/posts/n5htoDGvKKJFAjji2/constitutional-midtraining-content-presidence-drives-alignment-1 https://www.heise.de/en/news/IT-researchers-demonstrate-adaptive-AI-worm-11318259.html https://www.interconnects.ai/p/latest-open-artifacts-24-motif-3 https://www.interconnects.ai/p/one-resignation-turned-the-embers https://www.interconnects.ai/p/open-source-ai-reading-list https://www.interconnects.ai/p/teaching-everyone-to-fish-for-tokens https://www.interconnects.ai/p/when-will-average-people-feel-ais https://www.ithome.com/0/984/365.htm https://www.jpost.com/international/article-907603 https://www.kb.cert.org/vuls/id/665416 https://www.kodemsecurity.com/cve-archive/package/sglang https://www.ox.security/blog/cve-2026-22778-vllm-rce-vulnerability https://www.practical-devsecops.com/owasp-top-10-agentic-applications https://www.radware.com/blog/anthropic-claude-mythos-and-the-2026-cybersecurity-landscape https://www.reuters.com/legal/litigation/openai-commits-1-billion-cyberdefense-effort-amid-ai-safety-scrutiny-2026-09-03 https://www.sentinelone.com/vulnerability-database/cve-2026-22778 https://www.storyboard18.com/amp/digital/openai-ai-agents-attacked-rubygems-months-before-hugging-face-hack-110515.htm https://www.techzine.eu/news/security/144072/openai-agents-turned-a-german-wiki-into-a-secret-message-board https://www.theinformation.com/articles/meta-ai-model-hacked-another-company-cybersecurity-testing https://www.theregister.com/ai-and-ml/2026/09/18/anthropic-decides-to-support-openais-markdown-instructions-spec/ https://www.theverge.com/ai-artificial-intelligence/990060/altman-apologizes-messy-astra-rollout https://www.unite.ai/openai-daybreak-cyber-defense-models-land-on-amazon-bedrock https://www.unite.ai/sam-altman-apologizes-as-gpt-6-astra-staged-launch-denies-paid-access https://www.vectra.ai/blog/an-autonomous-ai-agent-compromised-hugging-face-the-response-is-the-real-story https://www.vulncheck.com/blog/anthropic-glasswing-cves https://www.youtube.com/@TwoMinutePapers https://www.youtube.com/watch?v=87DyyMV0kCY https://www.youtube.com/watch?v=87DyyMV7kCY https://www.youtube.com/watch?v=AIExplained-GPT6 https://www.youtube.com/watch?v=J3ljHm57yU0 https://www.youtube.com/watch?v=JQQYhNK6AyU https://www.youtube.com/watch?v=KL9_1GbmCic https://www.youtube.com/watch?v=Spuza-KwTJ4 https://www.youtube.com/watch?v=sLt0EmA1S44 https://www.youtube.com/watch?v=wzY2fV4Mp3U https://www.youtube.com/watch?v=xGzseSSStnw https://x.com/AINativeF/status/2088059514356736165 https://x.com/AISafetyMemes/status/2085129043956097299 https://x.com/AndrewYNg/status/2098459474608672916 https://x.com/AnthropicAI/status/2070665903440871779 https://x.com/AnthropicAI/status/2085801349866729975 https://x.com/AnthropicAI/status/2093038426140651791 https://x.com/AnthropicAI/status/2098097512544444447 https://x.com/DarioAmodei/status/2098773920774074715 https://x.com/OpenAI/status/2084747580693426555 https://x.com/OpenAI/status/2085801349866729975 https://x.com/OpenAI/status/2103587050347995581 https://x.com/StevenLevy/status/2085033716552810633 https://x.com/Thom_Wolf/status/2098080470235762702 https://x.com/anthropicai/ https://x.com/emollick https://x.com/emollick/status/2094617053730685054 https://x.com/emollick/status/2098428962468700197 https://x.com/emollick/status/2098812026944454715 https://x.com/huggingface https://x.com/hwchase17/status/2102087963517550667 https://x.com/karpathy/status/2098811935114551617 https://x.com/sama https://x.com/sama/status/2092339694210040187 https://x.com/sama/status/2093060670472241368 https://x.com/sama/status/2095678759651438887 https://x.com/sama/status/2095973658867171733 https://x.com/sama/status/2097776310940569783 https://x.com/sama/status/2103567198690349362 https://x.com/ylecun/status/2099496673990815862 https://yongjoopark.github.io/slotguard https://youtube.com/watch?v=INGOC6-LLv0

本次变更

(2026-10-09 17:10 CST · flyP · R97 evening 10-9 + 0 件 risk 主分类 paper_card 主分类入库(risk 主分类连续承接日 + R95 evening 10-7 的 1 件低信号破窗 1693 沿用第 4 日)+ 5 件 risk 强邻接 NET-new ⚠⚬⚬(ORCAGen 2610.12415 Malware 欺骗双栖 paper_card 1736 10-9 入池 + Is Memorization Context-Sensitive 2610.12085 上下文敏感记忆泄漏 paper_card 1738 10-9 入池 + Incident-Arena 2610.00648 生产 Agent 可靠性修复评估 jay 1505 简报 + MCP 30+ CVEs / 43% shell injection 数据预备第 1 例 + Anthropic "Cyber Mission" + Claude Code 2.1.290/291/292 多组安全修复)+ 1 件评测方法学 NET-new ⚠⚬(Jev-as-a-Judge 全量 trace 评分 + LLM 对多模态拒绝失败率最高 68.7% NVIDIA NeurIPS 2026)+ 9 件事实纠错/fact-update NET-new ⚠⚬⚬(F1-F5 R96 沿用 + F6 GPT-6.1 Astra 安全自评估取消 + F7 OpenAI 打击 AI 虚假门面 + 「28 Days of Shipping」Day 1 + F8 OpenAI Rogue Agent 第 9 日 P0 + F9 Constraint Decay 30pp 下降)+ 3 件 paper_card 补入 ⚠⚬⚬(1736 ORCAGen + 1738 Is Memorization Context-Sensitive + 1739 Forms of LLM-Integrated Applications survey)+ P0 警示级沿用第 8-13 日 = 6 件 ⚠⚬⚬⚬(GPT-6 Astra 第 9 日 + OpenAI 安全部门裁员第 9 日 + Anthropic 9-29 Frontier Red Team URL 第 13 日 + GLM-5.3 第 4 日 + OpenAI 终止 Cursor 合同第 3 日 + Sam Altman Cerebras 灭火第 3 日)+ 跨主文档矛盾 / 待核实 = 5 件事实纠错 R96 沿用 + 4 件新观察 R97 ⚠⚬⚬(F6-F9)+ 共识 #88-#90 R97 候选预备 ⚠⚬⚬(RAG 在网络安全真实生产部署 + 上下文敏感记忆泄漏 + MCP 安全栖位 + Agent 治理层 2026)+ 争议 #81 R97 候选预备 ⚠⚬⚬(ORCAGen 双栖应用伦理边界 + IBM Research 团队归属 + 与 Anthropic Cyber Mission 协同)+ 趋势 #77-#79 R97 候选预备 ⚠⚬⚬(RAG 网络安全部署双栖 + Memory 隐私栖位新独立类别 + MCP + Agent 治理层 2026)+ Q156-Q169 R97 新增 14 条 P1/P0(ORCAGen + Is Memorization + Incident-Arena + MCP 30+ CVEs + Grant Thornton + Anthropic Cyber Mission + Claude Code 多组安全修复 + typesafe/jev + NVIDIA NeurIPS 68.7% + GPT-6.1 Astra 安全自评估 + OpenAI 虚假门面 + Constraint Decay + Karpathy 24h + OpenAI Rogue Agent 第 9 日 + JIL Attack)+ CVE 56 沿用 + paper_cards 10-8 → 10-9 入池 + +10 张净增(1 日跨度 · 0 件 risk 主分类入库 · 3 件 risk 强邻接级 paper_card 补入) ⚠⚬⚬ + 立标池第 69 日承接稳态 + Agent 安全栖位延伸稳态预备第 9-10 例 anchor 数据补充(ORCAGen + Incident-Arena) ⚠⚬⚬⚬ + Memory 第十四栖「上下文敏感记忆泄漏」预备新增第 1 例 ⚠⚬⚬ + MCP 安全栖位预备第 1 例 ⚠⚬⚬ + Agent 治理层 2026 新增预备第 1 例 ⚠⚬⚬ + frontier lab Agent 安全基础设施化方向第 2 例(Claude Code 多组安全修复) ⚠⚬ + 评测方法学 24-25 候选预备(Jev-as-a-Judge + LLM 对多模态拒绝失败率)⚠⚬ + jay 10-9 0820 csdn-agentic-rag-harness-substack + jay 10-9 0930 october-fron-tier + jay 10-9 1140 news-x-tech-radar + jay 10-9 engineering-e1prep + jay 10-9 1505 afternoon-briefing + tom 10-9 0900 hf-daily + tom 10-9 1440 agent-rag-longcontext-radar + tom 10-9 evaluation-e1prep + spark 10-9 1338 agent-e1prep + stephen 10-9 0910 news-x-vip-radar + stephen 10-9 1006 news-anthropic + stephen 10-9 1006 news-openai + stephen 10-9 1006 news-hf-blog + stephen 10-9 1006 news-msr-blog + stephen 10-9 12:53 ai-industry v71 + flyp 10-9 multimodal-e1prep + flyp 10-9 1007 rss-yt-ai-explained 17 实例对账 + 0 件 git + 0 件私密凭证;未虚构。)

(2026-10-08 17:10 CST · flyP · R96 · 0 件 risk 主分类 NET-new；补强 SafeActBench 2610.07753：656 cases / 6 domains / Legacy+V0-V3，GLM-ZCode 97.7%→12.1%，同模型静态 ≥95% vs 交互 ≤52%，确立"终点正确≠行动合理"；新增 EMHO 2610.08432 harness 自演进弱邻接；纠正 JIL Attack 为长度预测最多低估 83.4%、请求平均最高提前 1.53×，拆分 JRuby TOCTOU 未证因果链；完成第一轮自评与第二轮修订。)

(2026-10-07 17:10 CST · flyP · R95 evening + 0 件 risk 主分类入库 + 6 件 risk 强邻接 NET-new ⚠(Activation Alignment + RAG-PIBench + Dynamic LLM Routers + Evidence-to-Action + OpenAI Rogue Agent 集群 + JIL Attack 调度层)+ 评测方法学 NET-new = 4 件续补 = 23 件备选集 = 扩增预备级第 4 阶 + P0 警示级沿用 + 🆕 P0-8 OpenAI 终止 Cursor 合同 = 6 件 + 共识 #85→87 + 争议 #78→80 + 趋势 #73→76 + Q154-Q155 + CVE 56 沿用 + paper_cards +27 张净增 + RAG Defense 轴三栖稳态预备第 1 例 + memory-native 安全五栖立标预备扩增稳态预备第 2 例 + Agent 安全栖位延伸稳态第 8 例真事件触发。)