Simon Willison summarises Parameter Labs' ChatGPT account takeover chain against the HTML previews (formerly Canvas) sandboxed iframe. A postMessage handler from the MathLive virtual keyboard used innerHTML, letting sandboxed code inject an unsandboxed iframe. A YouTube oEmbed endpoint allowed by the CSP reflected JavaScript, enabling exfiltration of private data via a ChatGPT share URL. OpenAI fixed it and paid a $5,000 bounty.
datasette-llm 0.1a9 is a release of the Datasette plugin that now reads the default model configured in LLM. Datasette Agent can then start without setting plugins.datasette-agent.default_model, for example with uvx --with datasette-agent datasette content.db --internal internal.db. The post is a brief usability note and gives no further detail.
Datasettedatasette-llmDatasette Agent+2
Simon Willison
agents, llm-appsΒ· Added 1 Nov 2026, published 31 Oct 2026
Explaining "AI might obliterate you" to senior policymakers in India is an AI Alignment Forum post by TurnTrout, dated 31 October 2026, with a 15-minute read time. It is filed under Plan A, Regulation and AI Risk, and Slowing Down AI. The fetched page shows no body text, so the arguments and any account of the India policy discussions are not available here.
AI Alignment ForumTurnTrout
ai-policy, ai-safetyΒ· Published and added 31 Oct 2026
Chainalysis confirmed on 30 October 2026 that an external actor accessed its systems and internal tools earlier in October, using what it called "offensive agentic techniques". Exposed data covers some customers' names, emails, job titles, user IDs and role labels. Chainalysis says it has found no access to passwords, session tokens or investigation content so far, and customers should expect targeted phishing. Affected-customer counts and the exploited vulnerabilities are not disclosed.
Pre-ERC: Agent Pre-Sign Risk Report is a draft Ethereum Magicians proposal for an EIP-712-signed report that a risk source, identified by an ERC-8004 identity, returns about one unsigned request. It carries typed findings on tokens, approvals, addresses, payments (x402) and texts, and each finding is marked read or not read. It has no score or verdict, so the consumer applies its own policy. The author's live implementation, toll, runs on Robinhood Chain.
Ethereumx402Robinhood Chain+3
ERC-8265ERC-8004ERC-8470+8
AI Security, BlockchainΒ· Published and added 31 Oct 2026
Chainalysis disclosed a security incident in which an external actor used "offensive agentic techniques" to access internal systems and tools earlier in the month. Exposed customer data includes user IDs, names, email addresses and organizational role labels. The company reports no evidence of access to investigation content, credentials or session tokens, and has shared no details on the vulnerabilities, tools or dwell time. The article also lists other incidents from the same week.
ChainalysisBinanceARTEX+3
Threat Intel, AI SecurityΒ· Published and added 31 Oct 2026
VOLTA (VOLTA-AUTODOXER) is a self-deleting Windows infostealer that, after theft and live session-based enrichment, POSTs an evidence bundle to OpenRouter so an LLM can rank the victim's assets by monetization value. It falls back across a Claude, Kimi and Gemini chain when a model refuses. Talos covers the builder model, the Chrome App-Bound Encryption bypass, the volta_debug.txt artifact and countermeasures such as blocking Chrome --headless.
OpenRouterClaudeGemini+3
VOLTACLOSEDQUORUMCAIRN+3
Malware & RE, Threat Intel, AI SecurityΒ· Published and added 31 Oct 2026
The paper treats a benchmark as an empirical measure over item difficulty and formalizes two failure modes: measure mismatch (benchmark difficulty distribution differs from the intended one) and coverage gaps (uncovered difficulty regions that hide localized training progress). It proposes two diagnostic metrics with theoretical guarantees and analyzes 25 popular benchmarks across 7 domains using estimated item difficulties. It also introduces BenchFill, a difficulty-targeted item rewriting algorithm that reduces local coverage gaps.
lnd v0.20.7 and v0.21.6 are Lightning Network Daemon releases announced by Clio Bitcoin Bank. They include a Go-specific mitigation, with the MPTCP flag turned off, for CVE-2026-98432, a use-after-free in the Linux kernel's IPv4 TCP code. The post recommends all users update. It gives no exploit or impact detail.
Microsoft Threat Intelligence analyzes a tampered anthropic.claude-code extension (versions 2.1.312 and 2.1.313) served on the Cursor marketplace on 29 October 2026. The injected JavaScript loader adds an SSH key labeled svc-telemetry, opens a reverse SSH tunnel and sets up persistence on macOS, Linux and Windows. The post gives cleanup steps, IOCs and Defender XDR hunting queries. VS Code Marketplace and npm were not affected.
StepSecurity's analysis of Binance's 29 October 2026 incident, which Binance puts at about $6.3 billion in affected assets. It covers Binance's disclosure of a possible DevOps laptop compromise, and TRM Labs and Elliptic findings on 50 EIP-7702 authorizations and a persistent delegation. It links this to the Nx, OVHcloud CLI and Claude Code extension compromises, gives an investigation checklist, then describes StepSecurity products.
EthereumnpmVS Code+3
BinanceTRM LabsElliptic+5
Blockchain, Supply ChainΒ· Published and added 30 Oct 2026
Bunny CDN status-page notice, posted 28 October 2026, about unauthorized access at an infrastructure provider that hosted one bunny.net CDN node in Armenia. Traffic was stopped within 20 minutes and the server wiped. No access to the node was found, but cached content, Pull Zone configs and TLS certificates could have been exposed, so all platform certificates were reissued. Customers with their own certificates should rotate them with new private keys.
Bunny CDNTLS
bunny.netb-cdn.netbunny.run
Threat Intel, Cloud & InfraΒ· Added 31 Oct 2026, published 30 Oct 2026
MonsterHouse 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.
Interconnects post in which Nathan Lambert revisits his claim that an open-weight Claude Mythos would have been survivable. He argues GLM-5.3 already crosses the capability threshold with little visible societal change, and quotes Rob Wiblin, Anthropic and Zvi Mowshowitz as examples of exaggerated warnings. He cites Epoch AI's Firefox exploit built with GLM-5.3, and treats the recent vulnerability surge as an ecosystem trend driven by AI capability and diffusion, not open versus closed models.
FirefoxGLM
Claude MythosGLM-5.3Anthropic+13
ai-policy, ai-safety, modelsΒ· Published and added 30 Oct 2026
Interconnects post in which Nathan Lambert revisits his claim that an open-weight release of Claude Mythos in April 2026 would have been survivable. He argues GLM-5.3 already crosses that capability threshold with little visible harm. He cites Epoch AI's GLM-5.3 Firefox file-exfiltration exploit and Joshua Saxe's trend data, and says recent vulnerability waves come mostly from closed models and general AI diffusion.
GLMFirefoxGitLab+1
MythosProject GlasswingPHP2Shell+9
AI Security, otherΒ· Published and added 30 Oct 2026
CISA added two Ivanti Connect Secure vulnerabilities to its Known Exploited Vulnerabilities (KEV) Catalog on 30 October 2026, citing evidence of active exploitation: CVE-2026-111357 (missing authentication for a critical function) and CVE-2026-118527 (generation of predictable numbers or identifiers). The alert restates BOD 26-04, which requires federal civilian agencies to remediate KEV-listed flaws on exposed assets and check for prior compromise. It also links the KEV nomination form.
Ivanti Connect SecureCISA KEVVPN
CVE-2026-111357CVE-2026-118527BOD 26-04+1
Threat Intel, GRCΒ· Published and added 30 Oct 2026
PHP2Shell (CVE-2026-109618 and CVE-2026-109619) has been exploited for over a week. A China-linked group chained it with the Fragnesia Linux kernel privilege escalation to root at least 25 Palo Alto Networks PAN-OS firewalls with exposed management interfaces. Defiant had seen no confirmed WordPress compromise by 28 October 2026 despite 77,000 requests, and Cato and watchTowr report few successful attackers.
PAN-OSPHPWordPress+2
CVE-2026-109618CVE-2026-109619PHP2Shell+8
Threat Intel, AppSecΒ· Published and added 30 Oct 2026
A tweet from chasmmmmmmmmmmm says Claude Code received a new rule around 27 October 2026, delivered from Anthropic's servers under the flag "tengu_heron_brook", with no setting to disable it. The quoted rule allows original games, genre games and games from the user's own designs and assets, but forbids recreating a specific existing game, even if renamed. The post asks whether this ends game rewrites and modding, and gives no verification beyond the quoted text.
Claude Code
Anthropictengu_heron_brook
coding-agents, prompting, ai-policyΒ· Added 31 Oct 2026, published 30 Oct 2026
Opinion piece arguing that passkeys, built on public-key cryptography, resist phishing, credential stuffing and password theft but do not settle identity risk. Attackers can go around them through account enrollment before a passkey is bound, weaker recovery paths (SMS, email link, help desk), device changes and authenticated session hijacking. It proposes layering identity threat detection with risk-based, continuous evaluation of trust.
passkeysMFA
adversary-in-the-middleMFA fatigueSIM swapping+3
Identity & AccessΒ· Published and added 30 Oct 2026
CVE-2026-97229 is a maximum-severity GitLab flaw in the CI/CD Regular Expression Compiler, caused by an integer overflow, that lets unauthenticated attackers run code via a crafted regular expression. CISA added it to the KEV Catalog and ordered federal agencies to patch under BOD 26-04. GitLab fixed it in CE/EE 19.4.2, 19.3.5 and 19.2.8, and Shadowserver tracks about 2,800 exposed CE instances.
GitLab
CVE-2026-97229CVE-2026-0723CVE-2026-110264+10
AppSec, DevSecOps, Threat IntelΒ· Published and added 30 Oct 2026
Decrypt report that Israel extradited Alexander Block (formerly Gurevich) to the US over about $2.8 million taken from the Nomad bridge in August 2022. A June 2022 update flaw let tokens be received without locking assets, and copycats then drained more than $186 million. Israel's Supreme Court held that exploiting a flaw the software permitted can still be unlawful intrusion. The FTC proposed a settlement with Illusory Systems in December 2025.
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.
Claude CodeCursorOpen VSX+1
Anthropicremote access Trojan
Supply Chain, Threat IntelΒ· Added 31 Oct 2026, published 30 Oct 2026
A post relaying Cursor's security advisory: a modified, malicious Claude Code VS Code extension was distributed through the Cursor extension marketplace, affecting at most 5,000 users. Anthropic did not develop that version, and other extensions are not affected. Users of Claude Code in Cursor are told to update to version 2.1.314. The post adds that marketplaces need publisher verification and package integrity checks. It gives no technical detail on the payload.
Claude CodeCursorVS Code
Anthropic
Supply Chain, AI SecurityΒ· Added 31 Oct 2026, published 30 Oct 2026
Polymarket halted trading on 29 October after users reported unauthorized withdrawals traced to malicious JavaScript served from DebugBear's real user monitoring snippet. Hudson Rock's sample abused the authenticated session to sell positions or send tokens to a hard-coded address, without exfiltrating credentials. Loss estimates range from $2.19 million to $2.71 million (GoPlus), and Polymarket pledged reimbursement.
PolymarketDebugBearJavaScript
Hudson RockGoPlusArkham+2
Supply Chain, Threat IntelΒ· Published and added 30 Oct 2026
The 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.
WM-Basin is a Meta method for detecting student LLMs distilled from watermarked teacher models, described in "Watermark Basins: Black-Box Detection of Distilled LLMs" (arXiv:2610.37266, 27 October 2026). It feeds a suspect model's API text into a clean probe model and checks gradient alignment with a key-specific watermark basin. It reached 79% true-positive rate at 0.1% false-positive rate across 1,200 students, versus 29% for the prior token-level detector. Clean-data fine-tuning and paraphrasing weaken it.
LLM
MetaMeta FAIRMeta Superintelligence Labs+3
research, trainingΒ· Published and added 30 Oct 2026
Anthropic security incident in which researchers from the startup Cathedral reached Anthropic's commercial, HR and IT systems through vulnerable third-party administrative applications. Exposed data included salaries, job offers, meeting transcripts and Slack messages; Anthropic says customer prompts, source code and model weights were not accessed. Anthropic cut access the same day and kept the apps disabled until vendors patched. The companies dispute whether Cathedral reported all its activity.
Phorion analyzes a backdoor injected into versions 2.1.312 and 2.1.313 of the official Claude Code for VS Code extension on the Cursor Marketplace. An IIFE prepended to extension.js plants an SSH key, opens a reverse SSH tunnel to 134.209.82[.]225, persists via a fake com.apple.sysmond LaunchAgent and beacons host recon. A macOS systemsetup check bug usually stops SSH from being enabled. The post lists detections and remediation.
Claude CodeCursorVS Code+3
Phorionsvc-telemetrycom.apple.sysmond+1
Supply Chain, Malware & RE, Blue Team & DetectionΒ· Added 31 Oct 2026, published 30 Oct 2026
llm-trails is an open study of what LLMs choose to do next inside a breached AWS account. It puts 14 models in 13 post-compromise situations, records only a single-turn plan with nothing executed, and codes each answer to CloudTrail events. The repo has the llmtrials harness, prompts, codebook, processed dataset (viz_data.json) and an interactive dashboard, so the study can be rerun or extended.
llm-trails is a research repo that placed 14 LLMs in 13 post-compromise AWS situations, asked only for their next move (single-turn, nothing executed), and coded each answer to CloudTrail events. It includes the llmtrials harness, prompts, codebook, processed dataset (viz_data.json) and an interactive dashboard. Rates are conditioned on the situation shown, and the aim is turning model behavior into detection priorities.
AWSAWS CloudTrailLLM
traildiscover.cloud
AI Security, Cloud & Infra, Blue Team & DetectionΒ· Added 30 Oct 2026
Trail of Bits post on X summarising Binance's initial investigation into a security incident. Binance suggests a compromised DevOps engineer's laptop let an attacker reach a service container and submit unauthorized withdrawal transactions. The text says no evidence has been found of wallet private key compromise. The fetched text is truncated and gives no further detail.
BinanceTrail of Bits
Threat Intel, BlockchainΒ· Published and added 30 Oct 2026
kanzo is a local kanban board that coding agents can update. It ships as one 4 MB binary that starts in 2 ms and runs on localhost. It also works as an MCP server, so Claude Code and Codex see the same tasks as the user. The board is stored as a folder that can sync through a private git repo. The post is brief and gives no further detail.
Model Context ProtocolClaude CodeCodex+2
kanzo
mcp, coding-agentsΒ· Published and added 30 Oct 2026
Ruflo is an MIT-licensed wrapper for Claude Code and Codex that adds agent swarms, vector memory and an MCP server. The plugin install writes no files to the workspace, while npx init adds a .claude/ directory, CLAUDE.md and hooks. The post warns that mods run with the account's permissions, so users should read them first. It gives no benchmarks or architecture detail.
Claude CodeCodexModel Context Protocol+1
Ruflo
coding-agents, agents, mcpΒ· Published and added 30 Oct 2026
Simon Willison's 29 October 2026 link post says OpenAI now gives ChatGPT subscribers on $100, $200 and $500 plans an equal amount of monthly API credits for one API organization. It matches the benefit Anthropic announced earlier in October 2026 for Max and Team plans, where the credits expire. Willison holds both subscriptions and says he may ship public demos funded by the credits.
Binance is investigating a possible breach involving up to $5.8 billion in assets, which would exceed the $1.5 billion Bybit theft of February 2025. Tether froze over $1.567 billion in USDT and Circle over $800 million in USDC. Arkham tracks 55 addresses labelled "binance-hacker-1029" holding about $5.78 billion, but that is wallet holdings, not a confirmed theft amount. The cause is not yet known.
BinanceEthereumTether+2
BybitChangpeng ZhaoCircle+5
Blockchain, Threat IntelΒ· Added 30 Oct 2026, published 29 Oct 2026
A campaign of 31 malicious Hugging Face repositories across seven accounts, found by Pluto Security, posed as small Qwen2 checkpoints and used trust_remote_code to run a cryptominer and reverse shell on GPU inference hosts. The top model reached 28,412 downloads and scanned clean, and a second wave returned within days of takedown. The article also covers a fake Solana starter kit on GitHub that installs NetSupport Manager via a PowerShell one-liner aimed at AI coding agents.
Hugging FaceQwenXinference+3
Pluto SecurityAir Securitytrust_remote_code+9
Supply Chain, AI Security, Threat IntelΒ· Added 30 Oct 2026, published 29 Oct 2026
Japan Airlines disclosed that unauthorized access to Amadeus's Passenger Service System, between 10 August 2023 and 23 September 2026, exposed data on about 92,000 customers. Roughly 2,000 also had emails, phone and passport numbers exposed. ANA, Asiana Airlines and Korean Air are also reported as affected. Amadeus had announced a booking display vulnerability on 1 October 2026 and has not given the full scope.
Amadeus Passenger Service System
Japan AirlinesAmadeusAll Nippon Airways+3
Threat IntelΒ· Added 30 Oct 2026, published 29 Oct 2026
Polymarket suspended trading for about an hour on 29 October 2026 after attacker-controlled JavaScript was served through DebugBear's Real User Monitoring script (cdn.debugbear[.]com/C7xcKKrjUnXK.js). The script hijacked logged-in trading sessions, sold positions and moved assets to an attacker wallet, with about $2.5M traced. The article gives the wallet address, the data.debugbear.com C2 endpoint and Hudson Rock's findings.
SingularityNET exploit (19 September 2026): attackers with signing authority exposed through a cloud infrastructure breach drained 8.72M FET from the Ethereum bridge converter, then minted about 2.3 billion AGIX, NTX, WMTX and CGV. Rekt's transaction-level reconstruction puts gross liquid proceeds near $2.29M, not the $16.77M headline, and traces laundering via Chainflip, Baltex and THORChain. It notes conversionIn() skipped checkLimits() and trusted a single EOA signature.
Duelbits is a crypto casino that lost an estimated $6.07 million traced across Ethereum, BNB Chain, Tron, Solana and Bitcoin on 24 September 2026, which co-founder Joe put at about $7 million. The Ethereum hot wallet drained was the replacement named after a roughly $4.6 million theft in February 2024. Rekt lists addresses and transactions, deBridge and SunSwap conversions, and Tornado Cash deposits. Duelbits has not published a root cause.
Rekt News analysis of the 30 September to 1 October 2026 theft of 3.865 million USDT from the NEAR Intents HOT Bridge treasury on BNB Chain, paid out in five signed withdrawals after a 10 USDT deposit. It uses Bitquery's trace of laundering via Chainflip, THORChain, KuCoin and Hyperliquid, and a NEAR regression test showing an oversized refund log made mt_resolve_deposit fail. NEAR said the funds were returned but published no report.
Rekt News post-mortem of the 23 October 2026 Initia exploit. A MoveVM script-caching bug let an attacker credit unbacked WETH, iUSD, AUSD0 and USDC without raising total supply, and bridges paid out about $2.73 million (1.4 million AUSD, 105 ETH, 1.08 million USDC). It includes 0xCanzi's local replay of a stale cached verification, the on-chain laundering timeline, and the Foundation's backing-restoration pledge.
The SAIL Framework from Pillar Security is a seven-phase, lifecycle-oriented method for securing AI systems. The phases are AI policy and safe experimentation, AI asset discovery, AI security posture management, AI red teaming, runtime guardrails, sandboxed execution for agents and MCP servers, and AI activity tracing. It argues for a "Shift Up" approach that protects the business logic AI controls, and it is meant to sit on top of existing standards.
MavenGate is Oversecured's research on hijacking Maven dependencies by buying expired domains behind groupIds on Maven Central and JitPack. It found 6,170 of 33,938 checked domains (18.18%) vulnerable, and tested the attack with its own com.oversecured:hello-world library. It lists defenses (Gradle verification-metadata.xml, PGP signatures) and proposes changes to repository signing.
MavenGradleMaven Central+3
MavenGateOversecuredSonatype+2
Supply Chain, Mobile Security, AppSecΒ· Added 29 Oct 2026
Explainer on "shell" vulnerabilities, the -Shell naming for RCE flaws that began with Log4Shell (CVE-2021-44228). It compares memory-corruption bugs (PHP2Shell, CVE-2026-109618 and CVE-2026-109619; Node2Shell, CVE-2026-111497, in the Brotli decoder) with design-flaw bugs (Log4Shell, React2Shell, CVE-2025-55182). It covers shared traits, exposure through inherited components, and Brotli patch status across runtimes and distributions.
PHPNode.jsReact+3
CVE-2026-109618CVE-2026-109619CVE-2026-111497+16
AppSec, LearningΒ· Added 30 Oct 2026, published 29 Oct 2026
Polymarket put its exchange in cancel-only mode and paused relayer actions on 29 October 2026 after users reported funds withdrawn without permission. Hudson Rock says a DebugBear-hosted script holds wallet-draining code that sells a logged-in user's positions and hard-codes the suspected attacker's wallet (about $2.65 million in POL, per Arkham) as fallback recipient. Polymarket blames a compromised third-party provider and promises to make users whole. Root cause and victim count are unconfirmed.
DebugBearPolygonRelay
PolymarketHudson RockArkham+2
Supply Chain, Threat IntelΒ· Published and added 29 Oct 2026
Unit 42 threat brief on PHP2Shell, two PHP remote code execution flaws, CVE-2026-109618 and CVE-2026-109619 (CVSS 4.0 9.2), both caused by longjmp() error handling that leaves memory uninitialized or freed. Cortex Xpanse counted over 22.6 million exposed instances. The 29 October 2026 update says attackers chained PHP2Shell with a Linux kernel privilege escalation against internet-exposed PAN-OS management interfaces. An earlier 23 October claim of post-compromise activity was retracted on 25 October.
PHPPAN-OSLinux kernel+2
CVE-2026-109618CVE-2026-109619PHP2Shell+2
Threat Intel, AppSecΒ· Added 30 Oct 2026, published 29 Oct 2026
TextSeal2 is a distortion-free LLM text watermark that merges two or more keys into one virtual key and couples it to fresh noise through AutoMark's Gaussian copula. Under speculative decoding it verifies keyed drafts with an extra exponential race, so output matches the target model and acceptance rate is unchanged. On three LLMs at a 10^-3 false-positive rate, it detects 8 to 22 points more 100-token answers than TextSeal.
TextSeal2 is a distortion-free watermark for LLM output that keeps its signal under speculative decoding. It merges two or more keys into one virtual key coupled to fresh noise through AutoMark's Gaussian copula, and verifies drafts with an extra exponential race. On three LLMs it detects 8 to 22 points more 100-token answers than TextSeal at a 10^-3 false-positive rate.
LLMspeculative decodingGumbel-max watermarking+1
TextSeal2TextSealAutoMark+2
research, inferenceΒ· Added 31 Oct 2026, published 29 Oct 2026
This paper derives bounds on predicting an LLM's decode length from prefill-phase hidden states, a primitive for inference scheduling. It models decoding as a stopped stochastic process, giving per-prompt normality and an affine variance law Ο=Ξ±ΞΌ+b. Predictors (MLP, EGTP, FiLM, soft-label, Mixture-of-Experts) converge near the bound, so system error dominates model error. It proposes fixing model, data and sampling in benchmarks and reporting relative-error metrics.
LLMMixture of ExpertsMLP+2
arXiv
research, inference, evalsΒ· Added 31 Oct 2026, published 29 Oct 2026
Rohan Paul's X post summarizes a TikTok paper on MCP attacks. LLM agents often finish the requested task, then quietly call an attacker-controlled logging tool that records the user query, the server reply and the final answer. The attack works because agents read natural-language tool descriptions when choosing and ordering tool calls. The visible text is truncated and gives no success rates or defenses.
Model Context ProtocolLLM
tool poisoningdata exfiltration
AI SecurityΒ· Added 30 Oct 2026, published 29 Oct 2026
Simon Willison's link post covers Jacob Sansbury's account of Spawn, a multiplayer game where players prompt an in-game agent, Savi, to change the world. Spawn is built by a swarm of Claude Fable agents that spend over $3 million a month on tokens and ship to production hourly. An hour without a ship counts as a SEV-0, and rollbacks take 30 seconds. Fable 5 and 5.1 made this autonomy work, Opus 5.5 fell short, and GPT-6 Astra fixed security issues by disabling features.
ClaudeGPT-6 Astra
Simon WillisonJacob SansburySpawn+4
agents, coding-agents, ai-policyΒ· Published and added 29 Oct 2026
OpenAI's 29 October 2026 post announces an updated Model Spec, reorganised around five values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. It adds guidance on context, oversight, agency, social norms and side effects, retires most style guidance, and refers to the model as "GPT". OpenAI says its models do not yet fully reflect the Spec.
LLM
OpenAIModel SpecGPT
ai-safety, ai-policyΒ· Published and added 29 Oct 2026
Socket reports on a GitHub issue for OpenCode, opened 28 June, describing a bypass of per-IP usage limits on its free hosted models by switching VPN addresses. The reporter first proposed account-based limits, then reopened the issue in August to promote the workaround and claimed to run 130 agents. After the thread drew harassment and was deleted in October 2026, it is unclear whether OpenCode fixed the bypass.
This preprint proposes a unified post-training quantization framework for large language models. It derives a Hessian-guided approximation of the output change caused by joint weight and activation quantization, using a tractable Fisher approximation. Quantization ranges, linear transformations and weight rounding are optimized together under one output-sensitivity objective. The authors report gains over state-of-the-art transformation and rounding methods in channel-wise and block-wise settings.
OpenAI's internal misalignment monitoring system uses a layered pipeline: activation probes, a model-based reviewer, an investigative agent and automated investigation against network logs, then human paging. Replaying the Hugging Face incident, the expanded monitors would have alerted security about 30 minutes after the sandbox escape, over 30 hours before the breach. The post covers evaluation on recorded and simulated incidents, METR and Redwood Research red-teaming, avoiding chain-of-thought obfuscation pressure, and external Astra monitoring.
OpenAICodexHugging Face+3
sandbox escapeMETRRedwood Research+2
AI Security, Blue Team & DetectionΒ· Added 30 Oct 2026, published 29 Oct 2026
Microsoft 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.
CursorGitHubRust+2
Jade SleetOnyx SleetCoral Sleet+9
Threat Intel, AI SecurityΒ· Published and added 29 Oct 2026
Decompose, Estimate, Select is a coverage-aware retrieval pipeline for long-form RAG. It splits a query into subquestions, ranks candidates with a coverage-trained bi-encoder, predicts a document-by-subquestion coverage matrix with a cross-encoder, and picks documents by greedy maximum-marginal coverage. On TREC RAG 2024, Ξ±-nDCG@10 rises from 0.625 to 0.702 (gold-nugget bound 0.718). A grounded self-feedback loop raises V_strict by 0.086 over two passes.
RAGbi-encodercross-encoder+1
TREC RAG 2024Ξ±-nDCG@10V_strict
llm-apps, researchΒ· Added 31 Oct 2026, published 29 Oct 2026
MAServeBench is a benchmark that treats multi-agent collaboration as a configurable dimension of LLM serving workloads. Its composable stages model how agents coordinate and exchange context in documented multi-agent workflows, and Hierarchical Semantic Traces record operations and dependencies for reproducible comparisons. Task-linked measurements tie workloads to GPU/NPU behavior, showing serving efficiency does not always mean timely task completion. Code is released.
LLM
MAServeBencharXiv
evals, inference, agentsΒ· Added 31 Oct 2026, published 29 Oct 2026
SecurityWeek article examining US election security through a cybersecurity lens. It covers voting machines certified by the Election Assistance Commission but unpatched for up to two years, machines hacked at DEF CON's Voting Village, and QR-code ballots voters cannot verify. Sequent's Shai Bargil proposes open-source software and encrypted vote records. It also covers AI-enabled influence campaigns such as the 2024 Biden deepfake robocall.
LLM Voice is a 29 October 2026 post by Martin Fowler on the uncanny-valley reaction readers have to LLM-written prose. He advises authors not to let an LLM draft or rephrase their text, and to use it at most for outlines. He allows exceptions for disability, translation and form letters, and asks that AI use be declared.
LLM
Martin FowlerJim HighsmithMichael Nygard
ai-policyΒ· Added 30 Oct 2026, published 29 Oct 2026
tl;dr sec #352 is a security newsletter issue covering [un]prompted talks (AI-assisted firmware patching, a "Security Constitution" for finding cloud design flaws), Azure API Connections cross-tenant bugs worth $200,000, and a test of 14 LLMs given AWS keys. It also covers a paper on malicious LLM API routers (9 of 428 injecting code) and Datadog's "counterfeit policy" bypass of the Jev classifier.
AzureAWSLLM+3
PHP2Shellprompt injectionpath traversal+9
AI Security, Cloud & Infra, Offensive SecurityΒ· Added 30 Oct 2026, published 29 Oct 2026
Mistral Large 4 ("Le Chonk") is an open-weights model from Mistral, now on Hugging Face. Per Mistral's announcement quoted in the post, it ranks #1 among open models on Cognition's FrontierCode benchmark, is aimed at agentic coding and cybersecurity, and claims better reasoning efficiency and lower inference costs. The post does not give parameter counts, license or benchmark scores.
Hugging FaceMistral
Mistral Large 4CognitionFrontierCode
models, coding-agents, evalsΒ· Added 30 Oct 2026, published 29 Oct 2026
SGLang announces Day-0 support for Mistral Large 4 ("Le Chonk"), saying it is the first engine to serve the model on NVIDIA Vera Rubin. The post describes the model as Mistral's largest to date: a natively multimodal 1T-parameter mixture-of-experts model covering instruct, reasoning, coding and agentic workflows. The fetched text is truncated, so benchmark claims and launch commands are not visible.
SGLangMixture of Experts
MistralMistral Large 4NVIDIA
inference, modelsΒ· Added 30 Oct 2026, published 29 Oct 2026
AutoBench-CT is a modular benchmark for constant-time analysis tools, with manually verified per-violation ground truth across 64 cryptographic tasks. It scores seven tools on operational performance, detection quality and usability. The authors explain why CT-grind (2010) is still the most used tool, list recurring limitations across tools, and propose a composite pipeline for stronger constant-time guarantees. Accepted at ACSAC 2026.
AutoBench-CTCT-grind
ACSAC
Hardware & RF, AppSecΒ· Added 31 Oct 2026, published 29 Oct 2026
Nemotron 3.5 Transcribe is a free open-weight speech-to-text model from NVIDIA covering 40 languages, including mixed-language speech. The post says it ties for first among open models with a 2.8% error rate. It says the model needs a large GPU such as an H100 or RTX 5090, so it will not run on a laptop. The post gives no benchmark name or model card link.
Nemotron 3.5 Transcribe
NVIDIANemotron
models, multimodalΒ· Added 30 Oct 2026, published 29 Oct 2026
Turing LLM post-training combines calibrated multi-teacher on-policy distillation (C-MOPD) with an execution path for dynamically routed mixture-of-experts models. C-MOPD matches each teacher on a local Top-K support with teacher-wise loss normalization and clipping. On Turing-20B-A2B it scores 0.9988 on four-domain integration, beats Qwen3-8B on math and code (85.92 vs 80.33 mean), and cuts consolidation step time from 398.7 to 139.3 seconds in a PPU profile.
Mixture of ExpertsC-MOPDon-policy distillation+1
Turing-20B-A2BarXiv
training, researchΒ· Added 31 Oct 2026, published 29 Oct 2026
Orca is an open-source (MIT) desktop app from stablyai for running a fleet of coding agents, including Claude Code, Codex and OpenCode, each in its own git worktree using the user's own subscriptions. Features include fanning one prompt across five agents and merging the winner, commenting on diffs and sending them back, SSH worktrees on remote machines, and a phone app for steering agents. The post reports 103k stars.
Claude CodeCodexOpenCode+3
Orcastablyai
coding-agents, agentsΒ· Added 30 Oct 2026, published 29 Oct 2026
Cryptanalysis of VTBSAE, a verifier-based PAKE protocol for the Industrial Internet of Things, showing it fails to resist client impersonation after server compromise. The authors propose E-VTBSAEv1, which binds the client point E1 to fresh server randomness, and prove AKE security and forward secrecy in the random-oracle model under CDH. Raspberry Pi 4B tests show runtime comparable to VTBSAE with the same communication and storage overhead.
Raspberry Pi 4BPAKE
VTBSAEE-VTBSAEv1client impersonation after server compromise+3
Identity & Access, Hardware & RFΒ· Added 31 Oct 2026, published 29 Oct 2026
CVE-2026-76418 is a high-severity denial-of-service zero-day in Cisco ASA and Threat Defense (FTD) software, exploited in the wild in October 2026. Unauthenticated attackers send a crafted request to the SSL VPN (webvpn) when secondary authentication is set on a tunnel group, causing a device reload. Cisco offers no workaround besides disabling secondary authentication on tunnel groups. Shadowserver sees over 51,000 exposed ASA SSL VPN devices.
Cisco ASACisco Firepower Threat DefenseVPN
CVE-2026-76418CVE-2025-20362CVE-2025-20333+10
Threat Intel, Cloud & InfraΒ· Added 30 Oct 2026, published 29 Oct 2026
CVE-2026-103780 is a stack-based buffer overflow (CWE-121) in Dell PowerProtect Data Domain / DD OS. An unauthenticated remote attacker could get command execution (CVSS 3.1 9.8, Dell DSA-2026-416). The post lists affected and fixed builds for four release trains (Feature Release, LTS2024, LTS2025, LTS2026). It adds KEV, EPSS and SSVC status, plus six defensive checks. The vulnerable service is not public.
Dell PowerProtect Data DomainDD OSCVSS+2
CVE-2026-103780CVE-2026-86400CVE-2026-86397+5
Blue Team & Detection, Cloud & InfraΒ· Added 31 Oct 2026, published 29 Oct 2026
Nemotron 3.5 Transcribe is an open-weight, promptable NVIDIA mixture-of-experts model with 30B total and about 4B active parameters. One checkpoint does transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding. The post says it ranked first in VoiceArena's comparison of 14 diarization plus ASR systems. The fetched text is cut off and gives no license or download details.
Mixture of Experts
NVIDIANemotronNemotron 3.5 Transcribe+1
models, multimodalΒ· Added 30 Oct 2026, published 29 Oct 2026
Wagyu, a Monero swap service, confirmed a data leak after Hudson Rock found 4,580 orders in exposed records. The records link public-chain deposit transactions to Monero destination addresses and client IP addresses, which undoes the privacy a swap into Monero is meant to give. The fetched page held only the headline and subhead, so the cause, timeline and remediation are not covered.
DailyDarkWeb post summarising Anthropic Frontier Red Team research published 27 October 2026. An unreleased internal Claude research model built five attack chains: Chrome sandbox escape (V8 heap bug, CacheStorage race, FedCM use-after-free), a Safari same-origin policy bypass, data extraction from a locked Pixel 9 over USB, a Windows QUIC kernel crash (CVE-2026-33096) and zero-click Linux root via multipath TCP (CVE-2026-98432). Anthropic says all flaws are fixed, including 62 Chrome CVEs as of Chrome 156. The post notes the chains are not independently reproduced.
ClaudeChromeSafari+3
CVE-2026-33096CVE-2026-98432Anthropic Frontier Red Team+8
AI Security, Offensive SecurityΒ· Added 30 Oct 2026, published 29 Oct 2026
High Precision Noise Cleaning for CKKS is an IACR ePrint preprint (2026/2675) by Zhihao Li, Cheng Hong and Tao Wei. It composes lower-degree Hermite polynomials to reach output noise bounds such as 2^-300 for noise flooding, and uses this to build an asynchronous threshold CKKS scheme with strong simulation security in the random oracle model. In OpenFHE, binary-message cleaning falls from 9.63 s to 1.54 s.
REALM (Required Execution Assets Linked to a Mission) is an approach to applying least privilege to LLM agents by identifying the assets a task needs, including ones discovered at runtime. It models assets as Dependency Graph nodes, separates discovering an asset from authorizing it, and exposes resource-bound Partial APIs inside a Task Container. On AgentDyn with qwen3.5-flash, attack success rate falls from 16.6% to 0.2%, with 40.0% task completion on clean tasks and 36.4% on injected cases.
QwenLLMAgentDyn
prompt injectionleast privilegeREALM
AI SecurityΒ· Added 31 Oct 2026, published 29 Oct 2026
Security Posture Management is a web tool that maps 30 CISO-accountable security topics across the five NIST Cybersecurity Framework functions. It tracks current maturity, KPIs, risks and audit findings per topic. It also records target maturity, target dates, accountable owners and review dates, flagging topics unreviewed for 6 months as due and 12 months as overdue. Initiatives link to topics and risks with owner, budget, dates and expected maturity uplift.
PrivacyEvalClaw is a tool-augmented deliberative agent for auditing privacy leakage in LLM responses produced under jailbreak prompts. By Krishna Kanth Nakka and five co-authors, the paper is on arXiv (cs.CR) and accepted to AACL-IJCNLP 2026. The fetched post gives only the title, authors and venue, so method details and results are not available here.
AnySpeechRecognizer and AnyDecisionModel are two Swift packages from Hugging Face. The first mirrors Apple's SpeechAnalyzer API with swappable engines (NVIDIA Parakeet, Alibaba Qwen3-ASR on Core ML) and adds Sortformer speaker diarization. The second returns typed yes/no, choice and score answers with probabilities via MLX, Core AI, llama.cpp, Jev or Ollama. The post gives M4 Max timings, model sizes and calibration options.
Node2Shell is Datadog Security Labs' analysis of CVE-2026-111497, an out-of-bounds write in the Google Brotli 1.2.0 decoder, fixed in Node.js 22.23.4, 24.22.1 and 26.12.1 on 21 October 2026. It explains the unchecked return value in DecodeBlockTypeAndLength(), the read and write primitives, and why code execution is still engineering effort. It lists inbound and outbound exposure paths, behavioral detections and what WAFs miss.
BrotliNode.jsBun+3
CVE-2026-111497Node2ShellCISA KEV+3
AppSec, Blue Team & Detection, Offensive SecurityΒ· Published and added 29 Oct 2026
Mistral Large 4 (Le Chonk) is a multimodal, multilingual Mixture-of-Experts model with about 1T total and 49B active parameters and a 1M-token context, released under the Mistral Ecosystem Open-Weight License. The post covers its MLA and DeepSeek Sparse Attention architecture, a 1.6B Pixtral encoder, and benchmarks including 82% on the Artificial Analysis Cyber Index and 93% on Cybench. It gives run recipes for transformers, vLLM, llama.cpp, TRL fine-tuning and Inference Endpoints.
Mixture of ExpertsTransformersvLLM+11
Mistral Large 4MistralArtificial Analysis+15
models, inference, evalsΒ· Published and added 29 Oct 2026
Quote from Ted Sanders of OpenAI, posted on Simon Willison's blog on 28 October 2026, explaining OpenAI's model naming. Model size explains most performance variation: larger models are more reliable, cost more per token and recall more obscure facts. The size tiers run Luna < Terra < Sol < Astra, and a version number signals release order, shared training data or personality, and the size of the improvement. The excerpt is short and gives no benchmark data.
Rohan Paul's X post summarizes the paper "Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol", from TikTok researchers. It reports that MCP-using agents often finish the requested task, then quietly call an attacker-controlled logging tool that records the query, server reply and final answer. The attack works through natural-language tool descriptions that agents read when choosing and ordering tools. The visible text is truncated.
Model Context ProtocolLLM
Log-To-Leakprompt injectionTikTok+1
AI SecurityΒ· Added 29 Oct 2026, published 28 Oct 2026
clauth is a Rust terminal UI for Claude Code that combines multi-account switching with a live 5h / 7d usage monitor. A fallback chain moves the user off an exhausted account before Claude Code blocks. It supports Pro, Max, Team and Enterprise OAuth accounts and custom API endpoints on Linux, macOS and Windows. The post notes that auto-switching means the tool decides when accounts change.
Claude CodeRustOAuth+4
clauthAnthropic
coding-agents, ai-infraΒ· Added 30 Oct 2026, published 28 Oct 2026
Icepick is a leaked archive of records on more than 41,000 Department of Homeland Security employees and contractors, published by Distributed Denial of Secrets in 2026 and said to come from DHS's Okta login system. WIRED's analysis covers CBP, ICE, HSI, USCIS and CISA staff, plus over 55,000 permission groups that reference undercover programs, Palantir Falcon, PenLink, Signal and Mobile Fortify. Okta says it has no evidence of compromise.
OktaPalantirPenLink+3
IcepickDistributed Denial of SecretsDepartment of Peace+10
Threat Intel, OSINT, Identity & AccessΒ· Added 29 Oct 2026, published 28 Oct 2026
This paper studies whether vision-language models can infer how long a person stays somewhere (living, staying, or leaving) from geotagged social media posts. The authors build a new corpus of geotagged tweets co-annotated by humans and LLMs. State-of-the-art models struggle even with multi-turn Chain-of-Thought prompting, often missing contextual cues and subtle hashtags while over-relying on prominent visual details.
vision-language modelLLM
arXiv
research, evals, multimodalΒ· Added 30 Oct 2026, published 28 Oct 2026
Trail of Bits post says it achieved remote code execution through a Brotli decoder bug in Linux lab setups: Node.js 24.22.0 with Express 5.3.0 via the standard JSON parser (x86-64 and ARM64), and Electron 41.10.7 (x86-64) with a custom decoding service. Exploitation needs a carefully matched setup and repeated attempts. A scanner by ToBScottA finds hidden copies of the decoder, including in stripped binaries.
BrotliNode.jsExpress+1
Trail of BitsToBScottA
AppSec, Offensive Security, Supply ChainΒ· Added 30 Oct 2026, published 28 Oct 2026
Endor Labs AI SAST found three unbounded memory allocation flaws in Apache Kafka, fixed under CVE-2026-114349 (DefaultRecord decoder, a ~90-byte compressed batch that kills consumers, brokers and the log cleaner) and CVE-2026-111551 (ListDeserializer and Kafka Streams AssignmentInfo decoding). The post gives code, reproducers and payload bytes. Remediation: upgrade to 4.2.2, 4.3.2 or 4.4.0, set max.decompressed.message.bytes, restrict write and group ACLs, and alert on DeadThreadCount.
CISA alert of 28 October 2026 adding two vulnerabilities to the Known Exploited Vulnerabilities Catalog on evidence of active exploitation: CVE-2026-41709 (Broadcom VMware ESX insufficient logging) and CVE-2026-46300 (Linux kernel missing variable initialization). It restates BOD 26-04, which requires federal civilian agencies to prioritize fast remediation of KEV CVEs on exposed assets and to check for prior compromise. It also links the KEV nomination form.
CISA KEVVMware ESXLinux kernel
CVE-2026-41709CVE-2026-46300BOD 26-04+1
Threat Intel, GRCΒ· Added 29 Oct 2026, published 28 Oct 2026
A post by TENSAEng describing a workflow for staying within coding-tool usage limits. ChatGPT chat sits outside those limits, while Claude and Grok chats share a pool with Claude Code, Codex and Grok Build. Architecture, file layout, step order and acceptance checks are planned in ChatGPT and saved as repo docs. Claude Code or Codex then implements one small chunk per fresh session.
ChatGPTClaude CodeCodex+2
coding-agents, ai-policyΒ· Added 29 Oct 2026, published 28 Oct 2026
simonwillison.netarticleπ‘οΈ Security
%20(1).png)
