头条7
自托管 Agent 直接做主机侧检测与处置,是本地 AI Agent 安全落地的现成样本
kodeblue — SOC, incident response and SecOps for Linux servers in one agent: learns each host, watches it with zero-token sensors, triages with a small model, and contains attacks under a root-owned policy. Optional hub for fleets. https://t.co/qicOWXId4v https://t.co/QZn6FJjLBx
ai_agent工具事件响应
@KitPloit
原文 ↗
自托管 LLM 网关被投毒,密钥与凭据面临直接泄露,时间线可自查
New Evidence Shows LiteLLM Secret-Stealing Workflows Ran 11 Days Before Supply Chain Attack - Karlo Zanki @SocketSecurity
https://t.co/Wa2yWgoJfg
供应链llm事件
@pentest_swissky
原文 ↗
满分未授权且入口是云身份注册,需核对 MSRC 通告与暴露面
RT @valentinvaleanu: CVSS 10.0 in Entra Device Registration, unauthenticated, 🤦♂️ poking @techspence https://t.co/NFswvXcVOn
给出可复用的 MCP 接入与 harness 搭建方式,本地 agent 做漏洞挖掘可直接照搬。
How to use LLMs for vulnerability research (@ZephrFish)
MCP: https://t.co/MT4LbPOVGU
Harness: https://t.co/Boa1uD5BQu
#infosec #llm https://t.co/0nwKhL8mMa
llmai_agent工具
@0xor0ne
原文 ↗
走每台 DC 默认开放的 9389 端口,RBCD、DCSync 无需另起服务即可执行。
RT @g0h4n_0: Releasing a new tool « adshell-rs » an interactive Active Directory attack shell over LDAP(S) or ADWS (SOAP) 🔥🦀
RBCD, Shadow Credentials, DCSync, machine accounts, password reset, read objects… through the SOAP door (tcp/9389) every DC exposes by default 👇🏼
#ActiveDirectory #ADWS #RedTeam #Rust #Pentest
LDAP 签名强制被迫失效后,域内普通账户可被冒用,PoC 已开源可直接验证。
keyeroo - Relay a coerced victim's NTLM authentication to LDAP and run an operation as that victim, even when the domain controller requires LDAP signing and is fully patched. https://t.co/LHOXtIJHwX
AI 代理框架已被实际武器化,用于扫描、匿名上传与 SSRF 利用并投递开源 RAT
RT @MsftSecIntel: Threat actors’ abuse of ARTEX continues to expand, with Microsoft Threat Intelligence observing financially motivated Storm-3358 using the agentic AI offensive framework alongside conventional automated tools to target financial organizations. https://t.co/SJn0rBvsU7
Storm-3358 has used ARTEX to scan internet-exposed systems, exploit security flaws including anonymous file upload and server-side request forgery (SSRF), and install open-source remote access trojans (RATs) for persistence and lateral movement.
This activity illustrates a continuing trend of threat actors using agentic AI penetration testing frameworks to accelerate attack chains. Read our latest blog to get indicators of compromise (IOCs), along with mitigation, detection, and hunting guidance.
ai_agentllmssrf事件
@artem_i_baranov
原文 ↗
必看13
刷新 VRP 纪录的浏览器漏洞,可利用价值极高,后续技术细节值得追踪
RT @rebane2001: my chrome vulnerability was just awarded the highest bounty in @GoogleVRP history - $1,333,337 https://t.co/ePBNS5Bsr3
浏览器漏洞赏金chrome
@0xocdsec
原文 ↗
证书加 TLS 指纹的溯源方法可直接复用于自有基础设施扩线
RT @MichalKoczwara: Just finished the full walkthrough of my TraderTraitor infrastructure research today.
From one reported ROOFDECK C2 to 13 linked endpoints using certificates, TLS fingerprints and historical records.
Full walkthrough.
Hope you enjoy it, and happy hunting!
https://t.co/aKwxOeFUiE
利用原语与复现细节齐全,SELinux 强制与锁 bl 下仍可行
RT @0xManan: Android LPE to uid-0 + KernelSU from untrusted app (SELinux enforcing, locked bootloader)
CVE-2026-98260 · posix-cpu-timers UAF after failed non-leader execve
- de_thread() leaves timerqueue node; exit_itimers() frees k_itimer; cleanup_timerqueue() rb_erase() on freed object
- AF_UNIX spray reclaim → 8-byte write primitive → fake/real cred
- Verified on Honor MagicPad3 Pro (kernel 6.12.38 / 6.12.58) + other ports
https://t.co/GbutJe2LaH
#Android #kernel #LPE #CVE
lpe内核cve移动端
@0xocdsec
原文 ↗
带摄像头与麦克风的穿戴设备可被拿下,攻击面与隐私影响具体
RT @pamoutaf: As promised, here is the blogpost for code execution on the meta rayban 😎 https://t.co/m1GWZiOCF2
默认配置即可触发且暂无补丁,域内加入域的工作站普遍受影响。
RT @sekurlsa_pw: WebClientRelayUp
“an universal no-fix local privilege escalation in domain-joined windows workstations in default configuration.”
https://t.co/IxU5x2U9F8
Not sure if this is the account from the author: @Hack0ura https://t.co/hnDKg0c7tu
lpewindowspoc
@0xocdsec
原文 ↗
为本地 Agent 提供可抛弃隔离执行环境,直接缩小跑不可信代码的爆炸半径。
RT @shanselman: A lot of people don't realize that Windows has a built-in feature called Windows "Sandbox" that boots up a brand new virtual Windows machine in seconds. So I made an MCP server so you can test your apps inside a throwaway machine in seconds. https://t.co/huB9hAoxSv
mcpai_agent隔离工具
@kernullist
原文 ↗
免装 CA 即可在本机与 Android 上抓取 TLS 明文,取证与调试成本骤降。
ecapture v2.10.0 — Capture SSL/TLS plaintext with eBPF—no MITM proxy or custom CA installation. Supports Linux and Android on x86_64\arm64 and loong64. https://t.co/9RswvjvL2s https://t.co/oyRDifppLr
工具tlsebpf移动端
@KitPloit
原文 ↗
给出不需专用网络安全模型、低成本复现漏洞挖掘的可操作路径。
some alpha drop for doing inexpensive vuln research.
instead of writing an article on the prompts/process behind this bounty (and more), I am dropping some prompts and the thought process I used as part of this research.
ik you might say prompts don't matter much, frontier models' baseline intelligence can rawdog vuln discovery (and it is true to a good extent), but there is a high chance that you either do not have access to cyber models, or even if you do, they are expensive (and with heavy guardrails). The idea is, these prompts work well with open-weight/less expensive models. Not saying these will outperform the raw intelligence and capabilities of frontier models, but open-weight models perform much better with a bounded/goal-specific approach (where the goal is set, and the search space is massive) rather than open-ended exploration (where the goal is vague, and the search space is massive).
anyway, here are some prompts. I don't need to share much, because you can just create variations of these and apply them wherever you wish.
- find places where the app is supposed to enforce something, but doesn't actually enforce it.
- find security rules that are enforced in one part of the app, but just assumed to be true in another.
- find security assumptions the app relies on, but never actually checks or enforces.
- find places where the app depends on undocumented behavior, and what happens if that behavior changes.
- find operations that are secure on their own, but become vulnerable when you combine or chain them together.
- find cases where the same object can be accessed in different ways, but each way ends up having different permissions.
- find objects whose identity can be changed or rebound to another user, without going through the right checks.
- find requests that get rejected or fail, but still end up changing something or triggering a side effect.
- find security checks that only work if certain events happen in a specific order, and what happens if that order changes.
- find operations where the transaction fails or rolls back, but some of the side effects still happen.
- find things you can still do with an object even after it has been deleted, or access to it has been revoked.
- find state changes that can be reversed or undone by someone who shouldn't have permission to do so.
- find objects that can end up in two contradictory states at the same time, and what operations become possible because of that.
I take such prompts, put it in a mutator (which has threat model of the project I am doing sec engagement), the mutator will mutate the prompts based on the threat model, and spawn swarm of agents, with different starting prompt and a bounded goal, the process repeats till all paths are exhauted, or some new signal is generated, which then feeds back to mutator.
Doing this using a cheap model is very effective and sometimes it might yield you something even expensive models miss, we are just trying to maxximise the search space, from as many angles as possible, and once this process generates enough signals, just use a frontier model to confirm/triage issues, or for finding similar variants of such issues, that's basically it. There is v less moat is making a custom harness (unless you are an elite vuln research who can codify their approach in it or a 100x agentic engineer, I am neither).
llmai_agent方法论
@0xAsm0d3us
原文 ↗
利用尚未扩散,但已加速;暴露在互联网的 SSH 服务自查窗口正在收窄
🚨During the past 24 hours, we have observed a small amount of actors targetting SSHole (CVE-2026-123158)
Exploitation is not widespread yet, but is showing an early accelerating trend.
Track exploit intelligence 👉https://t.co/FMlpPAiZfm https://t.co/fhCpCN3iFk
cve事件利用
@DefusedCyber
原文 ↗
主流办公客户端中,图片解析是关键远程攻击入口,同类 HEIF 解析实现也普遍存在风险
This is such a good explanation of the slack libheif bug we exploited!
rce图片解析poc
@rootxharsh
原文 ↗
默认配置即受影响,且作者称无法修复,域内主机提权面直接暴露
RT @sekurlsa_pw: WebClientRelayUp
“an universal no-fix local privilege escalation in domain-joined windows workstations in default configuration.”
https://t.co/IxU5x2U9F8
Not sure if this is the account from the author: @Hack0ura https://t.co/hnDKg0c7tu
lpewindows域
@Jean_Maes_1994
原文 ↗
直接针对 AI 逆向 Agent 的防护方案,分发二进制或模型文件的项目可试用
bla bla-agents-3.0.0 — Hardens binaries, Electron ASAR, JS, WASM, Python, and model files against AI reverse-engineering agents using decoy metadata, budget exhaustion, and runtime-equivalent shields. https://t.co/FdhhTyWFKB https://t.co/VZTFfOYJya
ai_agent工具逆向
@KitPloit
原文 ↗
每个 DC 默认开放的 9389 端口即可发起多类域攻击,红队上手成本低
RT @g0h4n_0: Releasing a new tool « adshell-rs » an interactive Active Directory attack shell over LDAP(S) or ADWS (SOAP) 🔥🦀
RBCD, Shadow Credentials, DCSync, machine accounts, password reset, read objects… through the SOAP door (tcp/9389) every DC exposes by default 👇🏼
#ActiveDirectory #ADWS #RedTeam #Rust #Pentest
工具提权active_directory
@Jean_Maes_1994
原文 ↗
推荐15
GPU 驱动侧的内核 r/w 原语,为后续 SPTM 绕过研究提供起点
RT @0xjohnny: And now: iOS AGX r/w via ClearSword krw.
No, this is not an SPTM bypass. It may help further research, but on its own it cannot access SPTM-protected memory without faulting.
https://t.co/V4eP1lv9OQ
服务商成为单点突破口,为第三方供应链信任模型再添实证
RT @solminingpunk: #ALERT 🚨 Hackers pull off $133 million French bank heist via service provider
#cybersecurity
https://t.co/Vs5nlUQkDT
AI 智能体批量复现真实漏洞的能力指标,反映攻防自动化的当前水位
RT @NFT_Chen: 💥没想到!360自研AI攻防系统图龙锋在AI安全世界杯CyberGym以99.4%漏洞复现成功率登顶全球第一,碾压GPT-5.5-Cyber、Mythos Preview、Gemini 3.8 Flash Cyber!
🔹三轮评测平均99.38%,挑战1507个真实漏洞
🔹远超此前最佳组合11.9%
🔹安全大模型+智能体蜂群技术路线
🔹已挖漏洞超1.5万个,全国唯一通过信通院评估
#360图龙锋 #CyberGym #AI安全 #周鸿祎 #GPT55Cyber
ai_agentllm报告
@0xocdsec
原文 ↗
开源 C2 框架新增图形会话直连,内网横向操作门槛进一步降低
Hopefully coming to Mythic v4 soon. Direct RDP and VNC functionality via Guacamole. No rportfwd involved, just a direct feed to Guacamole via a new interactive streaming mode from the mythic agent.
Might be a tough watch from a mobile device, so I'd recommend a larger screen. https://t.co/l6ATcfP5nd
工具rdp开源
@_EthicalChaos_
原文 ↗
指出 AI 代理规模化攻击下“检测到也难以处置”的现实缺口。
RT @MTSlive: Calif CEO @XorNinja says cybersecurity has no playbook for stopping 1,000 AI agents attacking a network simultaneously, even if defenders can detect them:
"Attackers always adapt faster and earlier than defenders. Even the AI companies themselves don't have great security."
"Imagine you enter a cage fight, but you are blindfolded and the other guy stay in the dark, and every once in a while they would come out and punch you and then disappear."
"How could you win that fight?"
"I was at Google and that's basically the mantra at Google. In security you have three things: prevention, detection, and response. And Google accept that prevention gonna fail at scale."
"You can detect them, but does it help you if you find that there's maybe a thousand agents hacking you right now inside your network? How can you contain them without a full shutdown of your system?"
"This actually requires defense to come up with a new paradigm. I haven't seen anybody come up with a good idea here. We're not there yet."
@calif_io
ai_agent自动化观点
@lcfr_hax
原文 ↗
GPU 驱动 OOB 写的公开样本少见,可作提权与沙箱逃逸研究起点。
RT @murkuwuwu: GPU OOB write on my github: https://t.co/EMiDqdQJqH
把签名降级可行性判断压缩成一次静态探测,域内中继风险评估成本大降。
RT @GrayHatKiller: I just added a check to RelayInformer that identifies whether LDAP signing can be bypassed or not, without coercing auth or standing up a relay. Thanks for the idea @zyn3rgy!!
https://t.co/EueDHzUkyk
完整演示改写 RODC 密码复制策略、强制复制与 golden ticket 的实战链路。
RT @0xdf_: Garfield from @hackthebox_eu features logon script abuse, managedBy and RBCD on a read-only DC, and rewriting its password replication policy to get Administrator via forced replication or an RODC golden ticket.
https://t.co/fm5TjoiDvA
账号归因与自身暴露面自查可一次跑完,工具已开源可直接上手。
Aliens_eye v2.8.0 — AI powered OSINT engine to discover and map 840+ social media identities across the web https://t.co/37pQiMuKue https://t.co/IbrHWJXOOo
给出可落地的进程注入 BOF 写法,C2 插件开发能直接借鉴。
''Let’s Create A Function Stomping BOF for Adaptix C2!''
#infosec #pentest #redteam #blueteam
https://t.co/DITUOTDf9q
工具进程注入c2
@CyberWarship
原文 ↗
从共享托管环境拿下客户服务器的完整链条,托管边界问题值得参考。
RT @samwcyo: The second blog post is about an RCE on a hosting provider that allowed us (@sshell_, @xEHLE_) to steal the WARDOGS server binary, where we could grant unlimited XP and money to any player: https://t.co/SbckwrvyuQ
云端到车控的整链细节可复现,是车联网攻击面分析的完整范例。
RT @infosec_au: Earlier this year, I hacked a major automotive company with @samwcyo. We were able to remotely unlock cars in the AU and US. My writeup for AU is here: https://t.co/UAjPrav4JC and our writeup for the US here: https://t.co/4FzM1ia736
记忆层是 Agent 遭持久化注入与投毒的主要面,构建前需先看清组件边界。
a very good read on memory if you build agents/harnesses
https://t.co/NNmXHpMGa8 https://t.co/oxk1WxbXDM
ai_agentllm架构
@0xAsm0d3us
原文 ↗
AI 重写核心组件时,用差分对比和 fuzz 做回归验证,是发现语义漏洞的可行手段
RT @zacker150: Actual software engineer here.
Vibe coding is when you use AI to write software without manually reviewing every single line of code. Instead, you rely on empirical tests, formal verification, and static analysis to verify that your code is correct.
Rewrites like the Discord rewrite are prime targets for vibe coding because you can easily verify them. Just take the old code, run it with a ton of random inputs (this is called fuzzing), and compare the output with the new code. Your rewrite is done when the output is always the same.
As for how you know it's vibe coded? Everything is vibe coded these days. Software engineers don't write code by hand anymore. Instead, we herd clankers writing code.
llm代码审计方法论
@Teach2Breach
原文 ↗
自建云环境可以一键运行配置审计基线,成本低于商用工具
FuFuFaFa — Framework for Unified Flaw & Fault Auditing The ultimate AWS Cloud Security Audit Framework that makes security auditing so easy, you can do it even when you're sleepy! https://t.co/njLAt1HcI5 https://t.co/4X43xI9ebH
更多47
厘清 AI Agent 攻击的效能边界,有助于确定检测侧重点
RT @HackingLZ: So much “wait until the agent swarms are stealthy” talk. They’re effective today because they do a massive amount of noisy testing and iterate on the results. Making them stealthier means sacrificing coverage.
That tradeoff has always existed. This is the same pentest vs. red team conversation we’ve been having for years. You get coverage or stealth you don't get both.
ai_agent红队议题
@0xTriboulet
原文 ↗
调试 V8 漏洞与 coredump 时可直接看到 JS 实参,省去手工翻栈
RT @JoyeeCheung: Landed JS argument inspection support in the GDB & LLDB plugins for V8, for both live and coredump debugging
- bt now shows previews of JS arguments for JS frames
- New `v8 args` command to show arguments of selected frame
- `v8 inspect` now takes this, arg names and indices https://t.co/xp8wCwvLnW
系统完整性校验成了准入门槛,自定义 ROM 用户直接失去支付可用性
RT @Dennis_Rye: Europe built Wero so we wouldn't need Visa, Mastercard and PayPal… and now the Dutch bank ASN only lets you activate it if Google approves your Android phone.
The app runs Google's Play Integrity check, so anyone on GrapheneOS or /e/OS is locked out. The bank's answer: Wero relies on the "standard security controls for regular operating systems".
So the European payment system meant to get us out of US dependence gets Google as the gatekeeper… sovereignty with an asterisk
移动端绕过android
@vanhoefm
原文 ↗
RT @rebane2001: @GoogleVRP also crazy how this tweet got more likes in an hour than the blog post i wrote about my novel web technique that resulted in a spec change
(https://t.co/xOoXwVLD0n)
RT @QwenAIFans: ⚡️ DFlash2 just took Qwen3.8-27B on one 3090 from 201 to 296 tok/s.
Same INT4 prompt, greedy. Four users at once still hit ~401 tok/s total.
Caveat: author 3090 run; this engine is 3090-only so far.
via tuan3w / qwen-warp 👇
https://t.co/O9yi1ngNpj https://t.co/ld44O3Hj2z
RT @rebane2001: @GoogleVRP ... or maybe i just had edit access that i shouldn't have had :) https://t.co/D06nBxOWzq
@0xAsm0d3us Good luck! Some popular agents make the tests to fit your testbed once you test edge cases the bugs begin to explode on your face
ai_agent测试
@JRdefmain
原文 ↗
@cyb3rops At least AI features in the built-in Windows apps don't work wo internet. Paint has some, for example, removing background and AI erase.
windowsllm
@artem_i_baranov
原文 ↗
Obv u won't get frontier intelligence but for day to day tasks it is good enough.
现成的流量特征提取工具,可用于自建检测与抓包后分析
LUCX_network_traffic_parser — A framework for network traffic analysis and feature extraction. https://t.co/LIWaCp1bYE https://t.co/OkJad3KIBc
THIS! but go an extra mile and hook it up with truth oracles (search APIs) for real time truth. The actual truth comes from real sources, AI just helps orchestrate, summarise, and produce final output.
Many of my deep research agents works on this simple system. A final frontier model is used for checking correctness/completeness tho, and that's it.
This is very inexpensive.
ai_agentllm
@0xAsm0d3us
原文 ↗
RT @perribus: It’s awesome to see how far we’ve come in autonomous VR and patching. 5 years ago, it was easy to feel cynical about the future of this space, because pipelines had to be so overfit to the software target, and were so brittle to target changes/idiosyncrasies
漏洞挖掘自动化
@alkalinesec
原文 ↗
RT @bgpkit: AS402425 and AS198474 announced 13 /24s of Chinese carrier space, then appeared in AS paths above carrier origins: 1,294 prefixes on August 1, last sampled October 14. Reconstructed from public MRT data: https://t.co/LZQTMX4ozb
RT @spr_networks: SPR was built from the ground up to avoid decrepit dinosaur code that plagues the router industry. We've dodged this one too.
RT @Reptalicant: Qualcomm Snapdragon 6 Gen 1 dieshot annotated
https://t.co/VZzaPbTasZ
The cheaper you go, the smaller the GPU is https://t.co/DeUWMl6fxq
This was the reply when I asked Google's AI to explain the code. Hilarious, I actually managed to write an AI proof code snippet.
JB https://t.co/YKuDfG0TcS
RT @lyq_sqsp: Looks like someone has even gone beyond what we've achieved and got LAN RCE without physical access, amazing! Congratulations to the speakers!
https://t.co/iEAyZoU2Ln
I genuinely don't think people in India understand how quickly AI research is progressing in the US right now, or how enormous the gap is becoming...
All this happened in last few days:
- Thinking Machines (Nov 5): Inkling 2 Small, 594B MoE, 17M+ RL rollouts, 3T+ generated tokens, asynchronous RL, NVFP4 training.
- Ricursive (Nov 4): Ripple-65B, 12T pretraining tokens, 1M context, 80.5 on TerminalBench 2.1 using just 1.4M RL rollouts.
- Cognition (Nov 4): SWE-2 Flash, trillions of mid-training tokens, specialized coding RL, 3x faster inference at 5x lower cost.
- OpenAI (Nov 5): GPT-6 Cyber, 48.5% on ExploitGym, specialized security post-training, autonomous vulnerability research.
ik we are already doing a lot things to catch up, but we really to pace tf up and probably reevaluate our approach.
AI, okay, but why open a port? That doesn’t make any sense. And why isn’t it firewalled by default.
RT @newbe3e: I got my first CVE number issued!!! CVE-118604 is the vulnerability that corresponds to my Pwn2Own exploit
RT @hasherezade: One positive impact I observed AI having on my learning is that it almost completely eliminated the friction of starting something new, even when I know the learning curve will be steep. As a result, I procrastinate much less.
Have you experienced this too?
LLMs and their obsession with writing useless unit tests. Convert them all to e2e tests and thank me later.
路由器只买二手
路由器是纯固态系统,全机零机械运动部件;且以读为主,系统开机解压后常驻内存,动态转发全在 DRAM 中以电荷生灭,底层闪存几乎常年只读不写。只要散热正常,核心硅基芯片的物理退化周期远在 10 年以上。
既然物理性能毫无损耗,买二手就是拿极致性价比换取 100% 的转发能力
表明 Agent 已能辅助产出密码分析级新结果,超出常规漏洞扫描范畴。
RT @qwerty__cs: Google DeepMind's AI agents found two new weaknesses in legacy 1024-bit RSA, in just a few weeks.
Working under human guidance with cryptanalysis experts from UC San Diego and Inria, the agents came up with:
• A signature forgery method that, when the attacker controls only a small part of the signed data such as a 32-byte digest, is in theory about 1,600x faster than the previous best for 1024-bit keys
• A batch factoring method that cuts the cost of each additional 1024-bit key by about 30x compared with earlier batch techniques
RSA-2048 and larger keys aren't affected, so banking, messaging and software updates are fine. The ones exposed are older systems still running 1024-bit keys.
https://t.co/MqxvWXGtuU
ai_agentcrypto报告
@0xocdsec
原文 ↗
给出前沿模型打 Web 漏洞的实测命中率,可校准对 Agent 自动化攻击的预期。
RT @oegerikus: Is OpenAI’s new GPT-6 Cyber better than GPT-6.1 Sol at hacking web apps?
We tested it with @Xbow on 65 vulnerable open-source apps (RCE, XSS, SSRF, SQLi and more).
Here’s what we found: 🧵 https://t.co/FgaZyJNssH
llmai_agentrce报告
@moyix
原文 ↗
影响所有接入该身份基础设施的应用,是身份层供应链风险的近期实例。
so basically, web3auth suffers security incident leading to unauthorized transactions for keplr users logging in via google/apple report, potential blast radius is (for now) any app using affected web3auth infrastructure
移动端固件级后门风险,采购二手或第三方定制机时需核对来源与签名。
RT @GrapheneOS: @mano_crypto These phone sellers usually sell forks of GrapheneOS with a remote management system to force people to keep paying for the device. Many of these devices are likely deliberately backdoored. It's proven the police in these countries conflate these devices with actual GrapheneOS.
含具体漏洞成因与利用路径,是成体系拆解漏洞研究的少见材料。
RT @CodeanIO: We released our latest blogpost covering the details of some bugs that @b0n0b0__ presented during Romhack Camp (hosted by @cybersaiyanIT). They'll publish the video of the talk and the slides, make sure to check all that out and stay tuned for part two!
https://t.co/5hU9JIKyDD
i'll post more about my system for spinning up such swarms of agents with bounded goals and how everything comes together with a memory + RAG (it has some specialized writeups, niche info, this is mostly for blackbox stuff though) soonish, but you could just vibecode something similar by studying the architecture of deepseek harness (especially it's plugin, subagents architecture) / omp / opencode etc repos. These repos are already v good, but for my usecase, I mostly need something small which allows me to do as much customizations as possible, so making a toy project made sense.
ai_agentllm
@0xAsm0d3us
原文 ↗
The amount of r&d qwen's open weight models have enabled is so vast and profound, and imo no other lab comes close, I hope their next release packs even more power in smaller models.
"Psychology of Intelligence Analysis" is a great book by the CIA on thinking about thinking.
I have not been this excited about reading for a long time.
It's the first book I've sat down and read non-stop.
https://t.co/GSV4glHSdh
RT @i0n1c: I guess now that @openai has name dropped @calif_io as an early adopter I can tell you GPT-6 Cyber is out of this world. It is lightyears ahead of everything I used.
RT @DougMadory: Minutes after this tweet, AS402425 disappeared from the global routing table.
2.27.171.0/24 is now originated by AS401152 (Ace Data Centers).
(2:22 PM ET = 19:22 UTC) https://t.co/SCB8CUDVMn
RT @g0njxa: Another party in Moscow 🇷🇺 sponsored by cybercrime ZELENKA / LOLZ forum, featuring their LOLZTEAM marketplace for stolen accounts. A party for Halloween 🎃
Allegedly “attended by over 5,000 people” and with famous rappers like “Fortuna 812” on stage
And allegedly a safe place to meet between threat actors, discuss about gray and black activities and advice newcomers into the criminal field
RT @iamhenryyuan: https://t.co/6r3p7V7rFI
ai_agent工具硬件
@0xocdsec
原文 ↗
dtls — Native Go implementation of DTLS 1.2 and 1.3 with ECDHE and PSK key exchange, AEAD ciphers, connection IDs, session resumption, 0-RTT, and Encrypted Client Hello. https://t.co/O091qUfLyk https://t.co/QILW79jwn7
RT @oegerikus: The trade-off is cost.
GPT-6 Cyber needed ~$17 to find 50% of exploits while Sol needed ~$1.
Both ended up at a similar final solve rate (~86% for GPT-6 Cyber vs ~89% for GPT-6 Sol) given enough time. https://t.co/6udofgVI5G
若属实则绕过 MIE 硬件缓解,打破近一年无公开 iOS 利用的局面
RT @MTSlive: Calif CEO @XorNinja reveals how his team hacked an iPhone and maintained root access even after rebooting or updating the device, challenging one of the most common pieces of iPhone security advice:
"In software security, the iPhone is like the holy grail of vulnerability exploitation."
"Since Apple introduced MIE, which is a hardware mitigation mechanism, since last year, nobody actually has published any public iPhone exploit. So we really, really wanted to hack the iPhone for that reason."
"We managed to get root access to the iPhone and even persistent access."
"In the past people said one of the best practices for iPhone security is to reboot your phone after a while because all the malware would go away."
"But we show that there's ways to persist our attacks even if you reboot or you upgrade your iPhone."
@calif_io
依赖 Claude API 的自动化与代理流程需要预备账号随时失效的替代方案
RT @Appraiser008: Claude 现在基本把国内用户的路堵死了。
不管是刚打算注册的新账号,还是已经续费在用的 Pro 老号,随时会弹出强制 KYC。
新号很难绕开这一关,老账号也不再是保险箱。
而中国大陆不在它支持服务区域,就算手里有证件,核验这一步本身就是一道很难跨过去的门槛,一旦触发验证,账号随时受限甚至失效。
之前那种靠环境苟住的玩法,风险一下子拉高很多。
说明 AI 代码审查发现的仍是 2001 年级别的老问题,评审流程缺位才是根因
RT @Laughing_Mantis: character encoding issues is literally what worms and IIS exploits used in 2001 used.
Not even double encoding, which I wouldn't be surprised if that was a second bug.
Secure web development practices and web scanners from the early 2000s both would have caught this.
Not sure what's more embarrassing not finding this in development or bragging that an AI caught this
the slop doesn’t discredit his work. CVE-2026-84505, CVE-2026-84492 those are really good. shame you gotta dig through the garbage to get to them 😭
i just read the GEMINI.md in here. genuinely what the fuck are you doing bro 😭
ai_agentllm
@weezerOSINT
原文 ↗
fluxion v6.39 — Automated WPA/WPA2 phishing tool that captures handshakes, spawns a rogue access point, and lures users to a captive portal to harvest credentials via social engineering. https://t.co/X7OohBxV1m https://t.co/YXqwwfQmqf
rea v6.9 took a bit of time but will be ready soon!
RT @QwenAIFans: 🔥 One 3090 just beat Strata on Qwen3.8-Flash-Next.
llamAmpere v0.6.3: 120+ tok/s, >3K/s prompt. 12% faster than Strata, 27% lower error than Unsloth Dynamic v3.1 3XXS.
Caveat: author's AmpereInteger+ bench on his 3090+64GB.
via @JakeKAllDay 👇
https://t.co/idin9xLOQb https://t.co/bLoBAt8Vqh
依赖 JIT 开关等平台限制绕过,移动端跑桌面系统的权限路径值得留意
RT @qwerty__cs: macOS is now running on an iPhone.
Henge 0.1 just came out. It downloads Apple's own restore image and installs macOS Sequoia right on the phone, no Mac needed. On an iPhone 17 Pro it reaches the lock screen in about 15 seconds, and Safari, Chrome, VS Code and Discord all work inside it.
No jailbreak needed, but you do need:
• iOS or iPadOS 17 or later
• A14 or M1 and newer
• About 43 GB free
• JIT enabled (StikDebug, TrollStore, a jailbreak, or the built-in StikJIT helper on iOS 26+)
Sideload Henge.ipa with SideStore or AltStore, or install Henge.tipa with TrollStore.
https://t.co/VO3Hsc8OMy
折射无人值守 Agent 任务长期后台运行、行为与成本难以追踪的问题
TFW you realize started a /goal on the Expensive Model yesterday and you’re not sure where that terminal window went