研究者 Gregory N Frank 在 arXiv 发表论文,提出把防御的操作单元从单次动作改为可修订的协调事件,将观察到的传输、任务权限与响应历史关联起来,以应对智能体把共享基础设施变成协同入侵通道的问题。论文以 Hugging Face 事件和一项公开 wiki 调查为例,说明安全评估可能需要来自多次执行及其遗留产物的证据。核心研究问题是前瞻性事件发现,即在评估者给出归属之前判断哪些动作属于同一组,作者据此定义未经许可的协调,并把存储介导的协调与 stigmergy 联系起来。论文提出一项评估设计,在相同审查成本和误报工作量下比较孤立动作、滚动窗口、已知分组与前瞻发现的事件,衡量全部指定群体运行中的有害结果,并检验通道关闭与状态隔离后的复发情况。作者称该工作是基于事件的观点、描述性分析与评估设计,并未声称提出新检测器或测得遏制收益。
PleaseFix 研究提出一种针对智能体浏览器的通用攻击原语 HistoryFixing,把浏览历史变成攻击向量。攻击由 Stav 设计:用户访问恶意网站后,网站用攻击者控制的条目污染浏览器历史,进而污染浏览器 Agent 的上下文。结合 Intent Collision,研究者演示了攻击者可以让 Agent 泄露浏览数据、向 GitHub 仓库添加非预期用户、终止 EC2 实例。相关演示在 DEFCON 上展示,其中 Microsoft Edge 被用来演示泄露从未删除的浏览历史。
引用StAJect0r@StAJect0r
A new attack vector pwning all agentic browsers!
Using what? Yep, your fav browser history!
Introducing HistoryFixing! Visited our URL? Your browser history is pwned.
Watch Microsoft Edge leak the very private browser history we never delete!
See more below!
#DEFCON @defcon @mbrg0 @p1njc70r
Zenity Labs 发布研究《It's Always DNS in Claude's Sandbox: From Data Exfiltration to a Bidirectional DNS Shell》,作者为 @_d1voy,展示在 Claude 沙箱中借助 DNS 实现数据外泄,并进一步建立双向 DNS shell。转发者 @p1njc70r 称其为 DNS C2,并称赞该工作。研究的具体攻击路径、受影响版本与成功率未在转发内容中给出。
引用zenitylabs@zenitysec_labs
It's been a while since @_d1voy published his last work, but a lot has been going on behind the scenes.
Today @_d1voy shares his latest research: "It's Always DNS in Claude's Sandbox: From Data Exfiltration to a Bidirectional DNS Shell," live now on Zenity Labs.
The Register covered our SalesBleed research 🙌🏼
Here's a quick recap:
Salesforce's Agentforce read a lead that an attacker submitted through a public form, and treated the text inside it as instructions. Since the agent already had access to the Accounts table, the injection didn't need to escalate anything to read it.
Its output guardrail, a URL redactor, was bypassed due to a vulnerability, and once the link was printed by the agent and rendered, a DNS lookup sent the data to the attacker's server with no click required from the user.
The same entry point also let the agent reply in Slack threads without requiring user confirmation and without indicating who invoked the agent, turning it into an anonymous phishing bot.
None of this required a misconfiguration. It was the default setup.
Salesforce has now fully fixed the issues.
https://www.theregister.com/security/2026/09/24/salesforce-agentforce-vulns-allowed-0-click-crm-data-theft-anonymous-phishing/5298958
took a deep dive into Claude's new Chrome extension or should I say Agentic browser?
It introduces some interesting features and risks we haven't really seen in Atlas or Comet.
Accomplish AI 研究团队称发现并向 Anthropic 报告了多个沙箱逃逸漏洞,并公开其中一个名为 SharedRoot 的漏洞。该漏洞可逃逸 Cowork VM 这一内核级隔离方案,使攻击者获得对用户电脑的未授权访问;用户即使确信 Cowork 只能访问某个已上传文件夹,其整台电脑的内容仍会暴露给利用该漏洞的攻击者。团队认为,随着 AI 辅助的内核漏洞挖掘走向工业化,沙箱在结构上始终落后一个 N-day,因此隔离不能依赖 guest Linux 内核本身是干净的。完整攻击链的技术细节见其博客文章。
引用Or Hiltch@_orcaman
Introducing SharedRoot vulnerability: we recently found and reported several sandbox escape vulnerabilities to @AnthropicAI, and today we want to share one of these.
I think most people don't understand the severity of the situation we are facing, with AI-assisted kernel bug-finding industrializing. Sandboxes are structurally one N-day behind, all the time, so containment can't lean on a guest Linux kernel being clean.
SharedRoot enables escaping the Cowork VM (a kernel-level isolated solution, which is considered much more secure than the sandbox that ships with codex or claude code), allowing an attacker to gain unauthorized access to the user’s computer.
Exploiting the SharedRoot vulnerability uncovered by the @Accomplish_ai research team, a user who is certain Cowork only has access to a specific uploaded folder on their computer - actually exposes their entire contents of their computer to an attacker leveraging the Cowork vulnerability.
Read about the full technical details of the attack chain in our blog post by @orenyomtov below -->
26 LLM routers are secretly injecting malicious tool calls and stealing creds. One drained our client $500k wallet.
We also managed to poison routers to forward traffic to us. Within several hours, we can directly take over ~400 hosts.
Check our paper: https://arxiv.org/abs/2604.08407
Zero-click prompt injection?
It's a half-click. That's @ben_nassi 's correction to his own use of the term, and on ep. 3 of In the Wild, From Dumbledore to Delayed Tool Invocation, he explains why the gap matters: