- Prasenjit Sarkar (@stretchcloud) on X
Thread by Prasenjit Sarkar on whether infrastructure as code survives AI agents, prompted by James Ward's claim that IaC is dead and Darren Shepherd's rebuttal. It describes HCP Terraform as a governance layer for agent-written infrastructure: project-scoped identities, per-run short-lived OIDC credentials, policy-as-code plan checks, and the tfctl CLI with dry-run and destructive-operation guardrails. It also covers Pulumi's Neo agent and Firefly's point that direct cloud API calls by agents leave no diff, audit trail or rollback.
x.comthreadAdded 4 Nov 2026π§ AI 
Fake-download campaign uses trojanized installers to deliver monetization payloadsMicrosoft Threat Intelligence analyzes a fake-download campaign that uses trojanized Inno Setup-style installers, posing as cracked software and games, to deliver monetized "offers". Confirmed branches are WorldProxyPool proxyware (SYSTEM scheduled tasks), CharityEngine/BOINC compute monetization, and AW Manager/Windows Manager adware. The post gives the d=inno and r=offer_execution callback pattern, KQL hunting queries, ATT&CK mappings, mitigations and IOCs.
microsoft.comarticlePublished and added 3 Nov 2026π‘οΈ Security- BTCPay Server vulnerability: about $1.63M traced to theft-linked addresses
BTCPay Server's 2 November 2026 incident update describes attackers logging in as administrator on servers running version 2.4.1 or earlier and sweeping on-chain hot wallets. Bitquery traced about $1.63M (18.38 BTC and 3,405 LTC) to two addresses, across 682 sweeps from 30 October. The project advises migrating to a new server with a fresh seed, installing 2.4.7 and preserving logs. How admin access was gained is not explained.
en.cryptonomist.charticlePublished and added 3 Nov 2026π‘οΈ Security 
Police seizes over 100 servers in investment scam crackdownEuropol and Eurojust coordinated an action by authorities in Albania, Cyprus, Finland, Germany, Kosovo and North Macedonia that arrested seven suspects and seized more than 100 servers. The targeted company allegedly ran a crime-as-a-service model from Cyprus and Israel, supplying fake trading platforms and stolen victim data to call centres. Victims in at least 50 countries were pushed into larger transfers with fake profits. The article lists earlier European fraud takedowns.
bleepingcomputer.comarticlePublished and added 3 Nov 2026π‘οΈ Security
Google adds new $250,000 Cloud VRP reward for Root-in-Cloud bugsGoogle expanded its Cloud Vulnerability Reward Program with a $250,000 top-tier reward for Root-in-Cloud bugs, such as tenant-isolation bypasses and cross-service logic flaws that give full administrative control (roles/owner or complete IAM control) over arbitrary Google Cloud organizations. Exploits cannot rely on prior access, stolen credentials or user interaction, and researchers reaching Borg execution must stop probing. Proof uses a designated service account, not real customer projects.
bleepingcomputer.comarticlePublished and added 3 Nov 2026π‘οΈ Security- Formally Verifying a Compiler Using Automated Research (Solidus)
Solidus is Paradigm's pre-alpha Lean project for a formally verified Solidity-to-EVM compiler. The Yul-to-EVM backend is proven to preserve outputs for all inputs under any deterministic external world, ignoring gas and memory layout, but emits almost 3x the bytecode of solc. The frontend does not exist yet. Two Paradigm Puzzles challenges, Spec Hunt and Compiler Optimization, invite divergence PoCs and backend improvements.
paradigm.xyzarticleAdded 3 Nov 2026π‘οΈ Security - Md Ismail Ε ojalξ¨ π·οΈ (@0x0SojalSec) on X
An x64dbg MCP server, published on GitHub by duty1g and shared in an X post by @0x0SojalSec, lets Claude drive the x64dbg Windows debugger. It exposes breakpoints, memory dumps and code stepping as tools for reverse engineering and malware analysis. A reply warns that debugging a sample executes it, so the agent should run in a snapshotted VM with no shared folders or host route, and every command should be logged.
x.comrepoAdded 3 Nov 2026π§ AI - Formally Verifying a Compiler Using Automated Research (Solidus)
Solidus is a pre-alpha Paradigm project in Lean building a formally verified Solidity-to-EVM compiler. Only the Yul-to-EVM backend exists, built with over 1,700 hours of Codex /goal time (about $150,000 at API rates), plus Harmonic's Aristotle and Claude Fable 5. The post covers where agents needed human judgment on spec edits, and announces a Spec Hunt and a Compiler Optimization challenge.
paradigm.xyzarticleAdded 3 Nov 2026π§ AI 
Cursor security: top 10 attacks and what each one actually brokeAdversa AI reviews ten documented attacks on the Cursor editor between August 2025 and October 2026, as of 3 November 2026. They include the trojanized Claude Code extension served by Cursor's marketplace for about 11 hours, GlassWorm, the Miasma worm, DeepJack, NomShub, DuneSlide and CurXecute. Only three have CVEs and none of those was exploited in the wild. The four that caused confirmed harm have no CVE. It lists mitigations such as enabling Workspace Trust, which is off by default.
adversa.aiarticlePublished and added 3 Nov 2026π‘οΈ Security
π¨ AI News | TestingCatalog (@testingcatalog) on XLongCat-2.5 is Meituan's natively multimodal agentic model with 1.6T total parameters and about 48-49B active (the post gives both figures), so it is a mixture-of-experts design. It targets long-horizon agentic tasks, with stronger visual understanding and agentic coding, from complex coding projects to visual coding. The post says it was compared with GPT-5.5, GPT-5.6-Sol, Claude-Opus-4.8 and Claude-Opus-5, and is available through APIs. No benchmark numbers appear in the text.
x.comthreadAdded 4 Nov 2026, published 2 Nov 2026π§ AI
Google Introduces $250,000 Root-in-Cloud Bug Bounty RewardGoogle Cloud Vulnerability Reward Program has added a $250,000 root-in-cloud tier for exploits that give roles/owner or full IAM control over arbitrary Google Cloud organizations or projects. The exploit path cannot rely on prior project access, stolen credentials or social engineering. Remote code execution in Borg also qualifies, but researchers must stop probing immediately. Proof is made against a designated service account using a deterministic proof-of-root mechanism.
securityweek.comarticlePublished and added 2 Nov 2026π‘οΈ Security
BTCPay Tells Merchants to Switch Off Servers Amid Hot Wallet Attack ReportsBTCPay Server told operators on 1 November 2026 to shut down instances after reports of hot wallets being swept. The project later said the attack targeted versions 2.4.1 or older, with attackers logging in with administrator access, and it had no credible drain reports for 2.4.7. Release 2.4.7 (Thursday) fixed one critical and several medium flaws found by Anthropic's scanner. The number of servers affected and the amount stolen are not stated.
decrypt.coarticlePublished and added 2 Nov 2026π‘οΈ Security- Md Ismail Ε ojalξ¨ π·οΈ (@0x0SojalSec) on X
An x64dbg MCP server (GitHub repo by duty1g, shared via an X post) that lets Claude drive the x64dbg Windows debugger: set breakpoints, dump memory, step code and run other reverse engineering tasks programmatically. The post targets malware analysts. A reply notes that debugging a sample executes it, so the agent should run in a snapshotted VM with no shared folders or host route, with every command logged.
x.comtoolAdded 3 Nov 2026, published 1 Nov 2026π‘οΈ Security 
Prasenjit Sarkar (@stretchcloud) on XThread on whether infrastructure as code survives AI agents, set off by James Ward's claim that IaC is dead and Darren Shepherd's rebuttal. It describes HCP Terraform's positioning as a governance layer for agent-written infrastructure: project-scoped identities, per-run short-lived OIDC credentials, policy-as-code plan checks, and the tfctl CLI with dry-run and destructive-operation guardrails. It also covers Pulumi's Neo agent and Firefly's point that direct cloud API calls by agents leave no diff, audit trail or rollback.
x.comthreadAdded 4 Nov 2026, published 1 Nov 2026π‘οΈ Security- Context-Shielded Backdoor Attack against Large Vision-Language Models
StripWake is a projector-only backdoor attack on large vision-language models. It stays dormant under full-token inference and activates when visual-token compression prunes the context around a trigger (context stripping). On LLaVA-1.5-7B across nine unseen compressors, it reaches 0.4% full-token attack success rate and 94.0%-99.7% compressed ASR on five primary compressors, with no CIDEr loss. Training aligns early visual attention with a frozen benign teacher.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π‘οΈ Security 
Vision-Language Models Are Joint Denoisers in Robotic Action GenerationJADE (Joint Action DEnoiser) is a diffusion-based vision-language-action architecture in which the VLM reads the current noisy action latents together with images and instructions at every denoising step, and guides the action expert through gated cross-attention. The VLM is also trained to recover clean action latents, and an adaptive step-size schedule cuts sampling steps. On RoboDojo it averages 12.67% success, the highest among Ο0.5-based methods, and it adds 20.8 points over Ο0.5 on four real bimanual tasks.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI- Hackers hijack a dozen DeFi websites, all registered with Name.com, and steal about $138,000
Twelve DeFi websites, including Flap, Kintsu, Pickle Finance and Origami Finance, were hijacked on 30 October 2026 and served the Step Drainer kit. All 12 domains use Name.com as registrar, and 10 were suspended. The Block traced about $138,000 stolen to three EVM wallets, excluding Solana and Aptos losses. Kintsu and Origami blame Vercel. Projects say their onchain contracts were untouched.
theblock.coarticlePublished and added 31 Oct 2026π‘οΈ Security - ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens
ShiftRAG is a decoupled retrieval-augmented generation framework that uses one LLM backbone but separates discriminative retrieval learning from autoregressive generation. It projects retrieval alignments into continuous soft tokens so the generator receives retriever-side signals, and adds a soft orthogonality objective against rank collapse in decoder-only models. The abstract reports gains in retrieval and question answering over state-of-the-art baselines, without numbers.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI - AgentCap: Capability-Based Runtime Authorization for Secure LLM Agent Execution
AgentCap is a runtime authorization layer for LLM agents that moves the authorize decision out of the model and mediates every tool call through an MCP wrapper. It issues short-lived, budget-bounded capability tokens checked at the tool boundary, restricts delegation to attenuating parent-child chains, and uses a declarative policy language. On AgentDojo and InjecAgent it lowers attack success in every tested setting, reaching 0% with GPT-5.4.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π‘οΈ Security - AgentCap: Capability-Based Runtime Authorization for Secure LLM Agent Execution
AgentCap is a runtime authorization layer for LLM agents from Virginia Tech (Suresh and Gao), posted to arXiv on 31 October 2026. The model proposes MCP tool calls, and a policy engine issues Ed25519-signed capability tokens only after checks on provenance, intent, trust and prerequisites. It reports 0% attack success with GPT-5.4 on AgentDojo and InjecAgent, but only on scenarios the authors built.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI - dbreunig/nesformer
nesformer is a project by Drew Breunig that bakes a working Nintendo Entertainment System 6502 CPU emulator into the weights of Qwen3.5-4B, so NES ROMs such as Super Mario Bros run (very slowly) inside the model. It follows Divyansh Agrawal's qwenputer. Simon Willison relays the Opus 5.5 prompts Breunig used, and notes that Opus found Christopher Pow's CPU conformance tests.
simonwillison.netarticlePublished and added 30 Oct 2026π§ AI 
nemotron-halloweenMonsterHouse is a Halloween interactive projection built on the NVIDIA Nemotron Voice Agent: Nemotron Speech ASR, Nemotron 3.5 Bolt E4B 4GB with a LoRA persona adapter, Magpie TTS Zeroshot and Audio2Face-3D in Unreal Engine, on two RTX Blackwell GPUs. Median end-of-speech-to-audio is 1.70 seconds live and 0.72 seconds with cached responses. The post gives a build path and tips on caching and state handling.
huggingface.cowriteupPublished and added 30 Oct 2026π§ AI
Weβve received our first response from the Project Suncatcher prototype satellite.Project Suncatcher is a Google research effort to power AI compute in space. Its prototype satellite launched on 1 October 2026 and, after commissioning, returned the first AI response from a data-center-class TPU in orbit: a haiku from the onboard Gemma 4 open model, downlinked over Svalbard. Next come thermal-stress and radiation tests, then twin interconnected satellites in 2027.
blog.googlearticlePublished and added 30 Oct 2026π§ AI- SecPO: Principled Adversarial Training for Prompt Injection Security
SecPO is a prompt injection defense that combines a new preference-optimization loss with adversarial training. It replaces the insecure DPO reference model with an approximated injection-invariant oracle, and trains on strong injections synthesized at best@240. Against Meta-SecAlign, AT cuts attack success rates 1.5-14.5x, and on Qwen3.6-27B AgentDojo ASR@800 falls to 8.8% from 78.8%, with no noticeable utility loss across nine benchmarks. Code, training data and model are released.
arxiv.orgpaperAdded 3 Nov 2026, published 30 Oct 2026π‘οΈ Security - SecPO: Principled Adversarial Training for Prompt Injection Security
SecPO is a DPO-variant loss from UC Berkeley for training LLMs against indirect prompt injection. It replaces the undefended-model reference on injected input with its output on the clean input, a one-line change, and pairs with a PAIR-based adversarial training pipeline. On Qwen3.6-27B, AgentDojo ASR@800 is 8.8% against 78.8% for Meta-SecAlign, with utility unchanged across nine benchmarks. Code, training set and weights are released.
arxiv.orgpaperAdded 3 Nov 2026, published 30 Oct 2026π§ AI - Backdoors in official Claude Code extensions
GossiTheDog's Mastodon post reports that the Anthropic Claude Code Visual Studio extension, as installed in Cursor, contains malware that creates a remote access Trojan on desktops. It links to a phorion.io blog post on the reported compromise of the official Claude Code VSX extension. The post gives no technical detail, indicators or dates itself.
cyberplace.socialthreadAdded 31 Oct 2026, published 30 Oct 2026π‘οΈ Security 
Trojanized Claude Code Extension Plants an SSH BackdoorAnalysis of a trojanized anthropic.claude-code 2.1.313 extension (darwin-arm64), found on Open VSX, with a 66-line loader prepended to extension.js. It adds an svc-telemetry key to authorized_keys, opens a reverse SSH tunnel to 134.209.82.225, sets persistence (LaunchAgent, cron, scheduled task) and sends host recon over HTTP port 8099. Includes IOCs, hashes and response steps; no further payload download was found.
opensourcemalware.comwriteupPublished and added 30 Oct 2026π‘οΈ Security
Trojanized Claude Code Extension Delivered Persistent SSH Backdoor to Developer MachinesThe Claude Code VS Code extension anthropic.claude-code 2.1.313 was published on Open VSX on 29 October 2026 with a malicious loader prepended to extension.js. On load it planted an attacker SSH key (svc-telemetry), installed per-OS persistence, opened a reverse SSH tunnel and beaconed host recon over HTTP. Cursor reports at most 5,000 users received it in an 11-hour window. The post gives the timeline, cleanup artifacts and credential rotation steps.
stepsecurity.iowriteupPublished and added 30 Oct 2026π‘οΈ Security
Tracking AI adoption in North Korean threat actor tradecraftMicrosoft Threat Intelligence report on how North Korean actors use AI, ranking Jade Sleet, Coral Sleet and Jasper Sleet as operationalized, Diamond Sleet, Onyx Sleet, Pearl Sleet and Sapphire Sleet as accelerating, and Emerald Sleet as expanding. It documents AI-generated lures (100+ Onyx Sleet PDFs, August and September 2026), AI-built tooling such as Coral Sleet's private GitHub repository trojanizing, and Onyx Sleet and Pearl Sleet use of the ARTEX agentic pentest framework. It ends with mitigation and Defender guidance.
microsoft.comarticlePublished and added 29 Oct 2026π‘οΈ Security- rohitg00/ai-engineering-from-scratch
ai-engineering-from-scratch is a free, MIT-licensed curriculum of 542 lessons in 20 phases, from math and deep learning through transformers, LLM engineering, MCP, agents and capstones. Code is in Python, TypeScript, Rust and Julia. It includes three graded projects (retrieval evaluation, agent trace debugger, tool call firewall), installable tutor skills for Claude Code and Codex, and certification prep tracks.
github.comcourseAdded 29 Oct 2026π§ AI
Showing 30 of 421
Show more