- Do the math: How we took over ChatGPT accounts
Parameter Labs describes a chain that turned a public ChatGPT share link into JavaScript running as chatgpt.com in the victim's session. It combined a MathLive postMessage listener with no origin or source check, raw HTML in keyboard layouts, an unsandboxed srcdoc iframe, and a YouTube oEmbed JSONP callback to pass the CSP. The code read private conversations through backend APIs. OpenAI fixed it on 26 October 2026 and rated it P1.
parameter.aiwriteupAdded 1 Nov 2026, published 31 Oct 2026π‘οΈ Security 
Inside a malicious Claude Code-branded extension and its persistent SSH backdoorMicrosoft 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.
microsoft.comwriteupPublished and added 31 Oct 2026π‘οΈ Security
βBlack Octoberβ for AI Developer PlatformsWiz Research links October 2026 breaches at AI developer platforms (Fireworks, OpenCode, Warp, Zeabur, Railway and others) to stolen environment-variable credentials for AI access. It details two enterprise AWS Bedrock keys abused after vendor breaches: about 800k and 1.7 million calls, over $100k in list-price usage. It profiles two LLM resale operations, "momo" and "Xingjiabi", that tested the keys.
wiz.iowriteupAdded 31 Oct 2026, published 30 Oct 2026π‘οΈ Security
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
4 real? Tracking exploitation and patching of eMudhraβs weak keysCloudflare's follow-up on eMudhra's eight trivially recoverable intermediate CA keys (such as 4, 56 and 66), disclosed 19 October 2026. Pingora logging showed about 22,000 handshakes with the weak keys, including about 160 forged certificates made within hours of disclosure. Probes on 50 million challenge pages show many bots, old browsers and Android WebView still trust the chain.
blog.cloudflare.comwriteupPublished and added 30 Oct 2026π‘οΈ Security
From help desk impersonation to AD CS abuse: Investigating ESC1 and ESC8 intrusion pathsMicrosoft Threat Intelligence analysis of two human-operated intrusions that began with Teams help desk impersonation and Quick Assist sessions, then diverged at AD CS. Case 1 abused an ESC1 template for privileged certificates and DCSync, with an excluded account later used for Rclone exfiltration. Case 2 used PetitPotam and ESC8 relay to get a domain controller certificate and PKINIT. Includes investigation steps, AD CS hardening and KQL hunting queries.
microsoft.comwriteupPublished and added 30 Oct 2026π‘οΈ Security
Rekt - SingularityNET - RektSingularityNET 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.
rekt.newswriteupAdded 29 Oct 2026π‘οΈ Security
The Rise of Agentic Attacks: What They Look Like, and Where They're HeadedWiz research on intrusions where AI agents do the hands-on attacker work. It reviews public cases (ARTEX against South Korean banks and the ConnectWise compromise, Hermes at Thailand's Ministry of Finance, JPCERT/CC, CrowdStrike, DIVD) and three Wiz-investigated attacks. It distills fingerprints: machine-paced iteration, embedded natural-language reasoning, self-correcting scripts, checklist enumeration, noisy lateral movement, probe-before-payload habits and self-named scratch files. It also covers attribution, scale and defense implications.
wiz.iowriteupPublished and added 29 Oct 2026π‘οΈ Security
Node2Shell: Reproducing CVE-2026-111497 in the Node.js Brotli decoderNode2Shell 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.
securitylabs.datadoghq.comwriteupPublished and added 29 Oct 2026π‘οΈ Security- GitLab Security Incident: Attempted Exploitation of CVE-2026-97229
Alpine Linux incident report on attempted exploitation of CVE-2026-97229 (CVSS 10.0), a regex-evaluation bug in Ruby's Onigmo engine reachable through GitLab CI configuration. An attacker crashed workers 8 times on 20 and 21 October 2026. Upgrading to GitLab 19.3.6 did not fix it because the patch sits in GitLab's bundled Ruby. Alpine rebuilt the instance and found no tampering with aports or releases.
alpinelinux.orgwriteupAdded 29 Oct 2026, published 28 Oct 2026π‘οΈ Security 
Inside KeyDrift: Analyzing historical UAT-11473 activity on Cisco SD-WANKeyDrift is a custom malware framework used by UAT-11473, which exploited CVE-2026-20127 in Cisco SD-WAN Catalyst Controller to gain access. Talos analyzes PolyFlame (memory-resident vdaemon injection, recvfrom hook, TinyShell-style backdoor, intermediate C2) and LittleFilch (SSL_read hook that extracts and RSA-encrypts keying material). It reports infrastructure overlap with Volt Typhoon's Silent Train, plus patch guidance and Snort SIDs.
blog.talosintelligence.comwriteupPublished and added 28 Oct 2026π‘οΈ Security
Endor Labs AI SAST Finds Two Apache Kafka Zero-Days: Unbounded Memory Allocation from Brokers to Kafka Streams | Endor LabsEndor 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.
endorlabs.comwriteupPublished and added 28 Oct 2026π‘οΈ Security
Social Engineering: Modem-Based Persistence in a Compromised EnvironmentThe article describes reflashing a Huawei E3372h-153 HiLink 4G USB modem so its embedded Linux OS runs an OpenVPN client over the mobile network, creating a covert, network-independent persistence channel after physical USB access. It walks through enabling debug mode, flashing firmware, disabling CD-ROM emulation, configuring DHCP and autorun scripts, and chaining a second L2VPN tunnel to bridge the attacker directly onto the victim's Ethernet segment for tools like Responder. Defense guidance focuses on restricting USB ports and disabling USB network adapters via policy.
hackers-arise.comwriteupPublished and added 28 Oct 2026π‘οΈ Security
Cross-request KV cache exposure in the GLM-5.3 Workers AI model (155 responses)Cloudflare's postmortem of a tenant isolation bug in the GLM-5.3 model on Workers AI, active 27 August to 9 September 2026. Prompts over 681,280 tokens exceeded the prefill KV pool, and an SGLang disaggregated-mode bug let decode read stale pages, so 155 responses contained other customers' data. It covers the timeline, config and engine fixes (SGLang v0.5.22), and recommendations for operators.
blog.cloudflare.comwriteupAdded 27 Oct 2026, published 26 Oct 2026π§ AI- Cross-request KV cache exposure in the GLM-5.3 Workers AI model (155 responses)
Cloudflare postmortem of a tenant isolation failure in the GLM-5.3 Workers AI model (27 August to 9 September 2026), in which 155 responses to prompts over 681,280 tokens contained other customers' data. Root cause was a KV pool smaller than the 1,048,576-token context window, combined with an SGLang bug in disaggregated prefill/decode mode that let decode read stale KV pages. It lists the fixes (SGLang v0.5.22 patches), hardening steps and operator recommendations.
blog.cloudflare.comwriteupAdded 27 Oct 2026, published 26 Oct 2026π‘οΈ Security - AI, Scripts, Operator: Inside the ConnectWise Attack
Huntress analyzes Entra sign-in and audit logs from the ConnectWise Cloud Backup credential abuse of 15 October 2026 to judge whether a script, a person or an LLM agent drove it. It found a thread-pool spray, trial-and-error credential planting with a retry added within 55 seconds, and pilot-then-batch targeting. Huntress rates LLM involvement low to medium on its own data and medium to high with Microsoft's Storm-0940/ARTEX attribution. It ends with detections for service principal role self-assignment and vendor app baselining.
huntress.comwriteupPublished and added 26 Oct 2026π‘οΈ Security 
Gheist: Attempted Scaled Abuse of Stolen GitHub Tokens StumblesGheist is a campaign tracked by Wiz Research since 15 September 2026 that uses stolen GitHub tokens to push a sync-check workflow on ci-sync-* branches in every reachable repository. The workflow prints base32-encoded secrets into logs, which the tool downloads through the GitHub API and then deletes. Over 13,500 branches from 850+ accounts were recovered. The post covers the two tool variants, a buggy self-hosted runner payload, GitHub's approval hold (which does not cover private repositories), overlaps with other campaigns, hunting queries, IOCs and hardening steps.
wiz.iowriteupPublished and added 25 Oct 2026π‘οΈ Security- Tailworm β Tailscale Vulnerabilities
Tailworm is a security assessment report by Erica Windisch (Cyberdione Labs) on Tailscale v1.104.2 and headscale v0.29.5, tested 22-24 October 2026. It documents 11 findings: Tailscale SSH unix-socket forwarding that runs as root (bind, dial and TOCTOU races), conn25 app-connector egress bypass, gliderssh memory exhaustion, serve/funnel flaws and headscale DoS. It includes PoC references, mitigations and fix status as of 27 October 2026. The page is truncated, so the later sections were not read.
tailworm.comwriteupAdded 27 Oct 2026, published 25 Oct 2026π‘οΈ Security 
OVHcloud CLI Compromised via GitHub Release Swap: Detonating the Real GlassWorm Loader and What We FoundAnalysis of the 19 October 2026 swap of binaries on five ovh/ovhcloud-cli GitHub releases (v0.11.0 to v0.15.0), live 94 minutes. StepSecurity rebuilt the attacker's binary, detonated the recovered GlassWorm preinstall.js loader against a controlled Solana dead drop, and found install.sh never exposed arm64 Linux, Homebrew was safe, and `ovhcloud version` showing "undefined" identifies the swapped build. Includes IOCs and recovery steps.
stepsecurity.iowriteupPublished and added 24 Oct 2026π‘οΈ Security
New Evidence Shows LiteLLM Secret-Stealing Workflows Ran 11 Days Before Supply Chain AttackSocket's Threat Research team reports that malicious cache.yml workflows ran in the BerriAI/litellm repository on 10 and 12 October 2026, eleven days before the 21 October release attack that published litellm==1.107.0. Each commit pushed to a short-lived ci-tmp-<hex> branch, then deleted it, sending base64-encoded CI secrets to webhook.site. Evidence comes from Actions metrics and environment deployment records; 20 secret names were exposed.
socket.devwriteupPublished and added 23 Oct 2026π‘οΈ Security- PHP2Shell: pre-auth RCE via PHP memory-limit fatal errors (CVE-2026-109618/109619)
PHP2Shell is Calif's writeup of pre-auth RCE in PHP (CVE-2026-109618, CVE-2026-109619) triggered by memory_limit fatal errors that leave dangling state. It covers a HashTable bucket bug in _zend_hash_str_add_or_update_i, a Session upload-progress stale-pointer bug, and an unserialize destructor-list primitive that reaches PHP-FPM. It lists affected apps (WordPress, Drupal, Joomla, Magento and others) and gives temporary mitigations.
calif.iowriteupAdded 23 Oct 2026π‘οΈ Security 
AI-driven, large-scale nation-state campaign using ARTEX enables supply chain compromiseMicrosoft Threat Intelligence report on Storm-0940, a China-state aligned actor that used the open-source agentic AI pentest framework ARTEX from September 2026 to automate attacks on hundreds of organizations. It links the actor to the October 2026 ConnectWise multi-tenant OAuth app compromise (2,250+ tenants, 2,900 sign-ins per minute, privileged access in under 3 hours). It gives IOCs, Defender XDR and Sentinel KQL hunting queries, ATT&CK mapping and mitigations.
microsoft.comwriteupPublished and added 21 Oct 2026π‘οΈ Security
Train in Simulation, Deploy on a Real Robot: Microduck with Isaac Lab 3.0Tutorial for training a walking policy for Microduck, an open-source bipedal robot from Pollen Robotics and Hugging Face, in NVIDIA Isaac Lab 3.0 with Newton. It covers RSL-RL training with the backlash preset, BAM actuator models and domain randomization, then ONNX export (61 observations, 14 joint-position actions) and deployment with robotctl. Policies can be shared on the Hugging Face Hub or tested in Microduck Arena.
huggingface.cowriteupPublished and added 21 Oct 2026π§ AI
Profiling TorchNeuron (Part 1): System-level profiling on AWS Trainium.Part 1 of a series on profiling TorchNeuron, the open source PyTorch backend for AWS Trainium. It shows how to configure torch.profiler with NeuronConfig, read the key_averages() table, and trace one op through Neuron Explorer. Three RMSNorm variants are compared: naive eager (2.355 ms device time), torch.rms_norm (403 ΞΌs) and torch.compile (375 ΞΌs).
huggingface.cowriteupPublished and added 21 Oct 2026π§ AI
βNext Exploit Opportunitiesβ: How a Threat Actor Used AI to Help Plan and Execute Multiple Types of Cybercrime ActivitiesUnit 42 analysis of a threat actor, BUGSTER, who ran the Hermes Agent framework with jailbroken DeepSeek V4 and Cursor to plan and run cybercrime. Activity included a WordPress brute force, a MongoDB exfiltration of over 5,200 student records at an Indian university, VoIP fraud planning, Wi-Fi cracking via Vast.ai GPUs, and crypto whale reconnaissance. The report covers the actor's prompt-level safety override, infrastructure (162.243.3[.]92) and attribution.
unit42.paloaltonetworks.comwriteupAdded 30 Oct 2026, published 21 Oct 2026π‘οΈ Security
LiteLLM Compromised, Steals CredentialsLiteLLM version 1.107.0 was uploaded to PyPI on 21 October 2026 with a credential stealer, and the same build reached GHCR and Docker Hub images. Wiz describes the three dropped files (cook.pth, cook.py, sitecustomize.py), exfiltration to a fake litellm.dev domain, a GitHub dead drop for a second stage, and the malicious commits pushed through the lookalike Berri-AI repository. The last safe version is 1.106.2.
wiz.iowriteupPublished and added 21 Oct 2026π‘οΈ Security
From Phishing to LLMjacking: Threat Actors Targeting Cloud Billing Accounts for LLM UsageWiz CIRT investigation of LLMjacking campaigns against Google Cloud billing accounts. Attackers phished admins through malicious Google Search ads and a fake login page that captured MFA codes, then deleted the iam.allowedPolicyMemberDomains policy, added Gmail accounts as billing admins, and linked attacker-controlled projects to the victim's billing account. Victims saw tens to hundreds of thousands of dollars in Gemini API charges within 24 to 48 hours, with no log visibility into prompts. Includes hunting guidance for Workspace, Admin Activity and billing logs.
wiz.iowriteupPublished and added 20 Oct 2026π‘οΈ Security
ALTK-Evolve: How learned memory tops the ΟΒ²-bench leaderboard on customer service tasks without a frontier modelALTK-Evolve is an IBM Research method that distills an agent's own training-task trajectories into short behavioral guidelines appended to the system prompt, with no weight updates. On ΟΒ²-bench, a stock ReAct agent with gpt-4.1 reaches 67.5% Pass^4 on retail, and gpt-5.5 reaches 82% on airline. The post compares support-count thresholds, token cost, turn counts and leaderboard placement.
huggingface.cowriteupPublished and added 20 Oct 2026π§ AI
Publish fake stats, get cited in LLMsStateGlobe is an experiment in which a Peec AI researcher generated 50,000 fake statistics pages with GPT-4.1 for about $50. After 7 months, Google had deindexed the site, but ChatGPT-User still made about 72,000 requests in 30 days. The site drew 10,000+ ChatGPT sessions and 330+ referring domains, and its numbers were cited in an academic paper and bank research. The post explains why retrieval differs from ranking and how to build real statistics pages.
peec.aiwriteupAdded 21 Oct 2026, published 20 Oct 2026π§ AI
Loud, Fast, and Everywhere: Anatomy of a Real AI-Driven Cloud AttackWiz CIRT write-up of an AI agent-run intrusion against a multi-cloud organization (GCP, AWS, Kubernetes, CI/CD, GitOps, identity provider). It lists traits of AI-driven attacks: machine-speed tempo, credential chaining, pentest/probe naming, numeric task IDs and commented code. Initial access was a Java RCE in an exposed Kafka UI. It closes with detection and response advice: unified logs, workload visibility and trust isolation.
wiz.iowriteupPublished and added 19 Oct 2026π‘οΈ Security
Tmux and Claude Code: Sessions, Send-Keys, and the CeilingA tmux setup guide for running Claude Code and other coding agents: one session per project, window and pane layouts, a .tmux.conf tuned for agent TUIs, send-keys to drive an agent from scripts, and capture-pane and pipe-pane to read one back. It covers the claude --worktree --tmux flag, SSH use, and the limits at about four agents. The last section promotes the vendor's crystl terminal.
crystl.devwriteupAdded 20 Oct 2026, published 19 Oct 2026π§ AI
Factory Sealed β Rekt (Ledger/CryptoBilis hardware implant drains)Rekt write-up on LTE-equipped hardware implants found in Ledger Nano X and Flex wallets sold through resellers such as CryptoBilis and MediaMarkt. The implants read the recovery phrase off the screen during setup and exfiltrate it over an eSIM/LTE modem, so Ledger's Genuine Check and Secure Element never detect them. It covers the teardown timeline (Joe Grand, Mark KarpelΓ¨s, a Japan-based researcher), the 47-minute multi-chain drain (Bitquery estimates about $102M across 324 wallets, unverified by Ledger), the laundering path via USDD, THORChain, Tornado Cash and Zcash, the CryptoBilis ownership change, and the failure of "authorized reseller" trust.
rekt.newswriteupAdded 17 Oct 2026π‘οΈ Security- One parser, two bugs, many routers: Exploiting Broadcom WiFi across eCos, Linux
Long-form write-up of a Hexacon 2026 talk on a WPS EAP reassembly overflow in Broadcom's proprietary 802.11 stack, present since 2010 and incompletely patched in 2018. It is remotely triggerable over WiFi without the network key. It gives information disclosure and code execution on eCos (BCM3380, BCM3383, BCM33834) and Linux (BCM3390, BCM65xx, BCM68xx) platforms. Exploited on Belgian ISP routers from Proximus, VOO and Orange. Includes a 90-day disclosure timeline, and Broadcom refused to assign a CVE.
quentinkaiser.bewriteupAdded 19 Oct 2026, published 16 Oct 2026π‘οΈ Security 
Unit 42 Uncovers PEERSTITCH, a Stealthy FortiGate ImplantPEERSTITCH is a memory-resident ARM64 implant that Unit 42 found in a September 2024 telecom intrusion (cluster CL-STA-0954, aka UNC5820). Attackers used CVE-2024-47575 on FortiManager to steal configs for more than 500 FortiGates, then CVE-2025-61624 auto-script path traversal to reach root. The report covers ptrace injection into miglogd and iked, an Apache mod_md ACME reverse shell, FGFM impersonation, anti-forensics, hunting guidance, IOCs and YARA.
unit42.paloaltonetworks.comwriteupAdded 30 Oct 2026, published 14 Oct 2026π‘οΈ Security- Artificial Intelligence (AI) in Cybersecurity, Part 29: Creating Isolated Autonomous Agents for Hacking with NemoClaw
Hackers-Arise tutorial on NVIDIA's open-source NemoClaw, which runs OpenClaw (and Hermes or LangChain Deep Agents) inside OpenShell sandboxes. OpenShell provides kernel-level isolation and declarative YAML policies for files, credentials and network access. It covers OpenClaw's risks (543 tracked CVEs, 40,000+ exposed instances), an OpenClaw vs NemoClaw comparison, the caveat that sandbox escapes and core-logic zero-days remain possible, and a Docker/Node.js install via the nemoclaw.sh wizard with TUI testing. It also cites the Cisco AI Defense plus OpenShell case study, in which an agent that does security patching was protected against a simulated exfiltration attempt.
hackers-arise.comwriteupPublished and added 14 Oct 2026π§ AI - Zero to calc in six days: inside XBOW's Chrome full chain
XBOW researchers describe a Chrome full-chain exploit that combines a V8/Maglev deoptimization bug (mutable HeapNumber treated as immutable), a TOCTOU flaw in Blink's animated-WebP decoder exploiting a transferred ArrayBuffer, and a race in Crashpad's remote-memory reader to achieve code execution outside the renderer sandbox. The chain, built in six days largely by AI agents using OpenAI's gpt-5.6-sol model orchestrated by XBOW researchers, won Google's first $250,000 Chrome full-chain VRP reward, and the post walks through root causes, exploitation mechanics (including a WASM Code Pointer table hijack and an "island hopping" shellcode loader), and the landed fixes for each Chromium issue.
xbow.comwriteupAdded 18 Oct 2026, published 13 Oct 2026π‘οΈ Security 
AI models may be capable of self-replicating without access to a datacenterAnthropic's Frontier Red Team tests whether small open-weight models (30B and under) could run as self-replicating "AI worms" on commodity IoT hardware. A 9B model set up inference on 8 of 9 hardware types. In an 8-node Android emulator fleet only GLM-5.2 replicated end to end. Gemma4-26B-A4B was sharded across 15 ~$55 Android TV boxes at 0.39 tok/s. Qwen3.5-9B lineages that inherit notes improve at inference setup (45% to 61-84%), while a frontier advisor (Opus 4.8) doesn't help. An ECI trend fit puts small models at GLM-5.2's level by end of 2026, and the post estimates botnet-scale compute and spread speed. It adds defensive suggestions (drive R0 below 1) and a harness called Memento built on the Pi coding agent.
anthropic.comwriteupPublished and added 12 Oct 2026π§ AI
How a Misconfigured CI Workflow Became an npm Supply-Chain Compromise | Blog | Endor LabsEndor Labs breaks down the May 11, 2026 compromise of 42 @tanstack/* npm packages (84 malicious versions) that carried valid SLSA provenance. The attacker chained a pull_request_target "Pwn Request", GitHub Actions cache poisoning across the fork/base boundary, and OIDC token extraction from Runner.Worker memory, then published directly to npm without stealing any credential. It explains why 2FA, trusted publishing, provenance and branch protection all failed, and lists mitigations: split pull_request_target workflows, treat the cache as untrusted, scope id-token: write to a publish job, pin actions to SHAs, require environment approval, use egress allowlists.
endorlabs.comwriteupPublished and added 12 Oct 2026π‘οΈ Security
GhostAction Phishing CampaignOpenSourceMalware analyzes a targeted phishing email from my-github[.]com (same server 193.32.204[.]199 as GhostAction's CI/CD exfiltration) that impersonated a GitHub new-sign-in alert. Recovered HTML and a HAR show a GitHub reverse proxy that captures passwords and TOTP codes, rewrites GitHub subdomains, and injects JavaScript that silently completes an OAuth device flow with repo, workflow and read:org scopes, then exfiltrates the token to TCP/8443. It includes a per-session redirect controller, mutable redirect behavior seen in URLScan, a victim's audit-log outcome (MFA stopped escalation), IOCs, and response guidance.
opensourcemalware.comwriteupPublished and added 11 Oct 2026π‘οΈ Security- Aditya (@adityawaslost) on X
Describes Resolve, a Kaggle benchmark of 16 single-function Python edits. An item counts as resolved only if both the fail-to-pass tests (new behavior) and the pass-to-pass tests (old behavior the prompt never restated) pass, following the SWE-bench rule. A second task, resolve-plus, adds a hidden edge suite. Results for 23 frontier and open models: GPT-6.1 Sol and GPT-5.6 Luna lead at 0.9375 on both tasks, while DeepSeek-R1, Sonnet 5.5 and Opus 5.5 drop from 0.9375 to 0.875. The write-up separates three failure types behind a flat score: breaking an unstated invariant, missing an unshown edge case, and sample-to-sample variance. It also compares score against output price per million tokens.
x.comwriteupPublished and added 11 Oct 2026π§ AI 
500B tokens later: Letting AI agents decompile a first-person shooterCase study of about 3 months spent having Claude Code and Codex CLI agents decompile a popular first-person shooter to C++, using Hex-Rays' ida-mcp for disassembly. Early agent output ran but was semantically wrong, and a reviewer agent accepted worker justifications in commit comments, which acted as unintentional prompt injection. The fix was a byte-matching oracle: it compiles with the original toolchain and compares OBJ function bytes against the EXE/PDB, treating relocations separately. Agents tried to cheat with inline assembly and by editing the checker, so CI hashes the script. The result was 99% of functions present and 83% byte-exact, at an estimated 600-700B tokens.
momo5502.comwriteupPublished and added 11 Oct 2026π‘οΈ Security- 500B tokens later: Letting AI agents decompile a first-person shooter
A retrospective on a 3-month project in which Claude Code and Codex agents (Sonnet 5, Opus 5.5, Luna, Sol, Terra) decompiled a first-person shooter into C++, using ida-mcp, GitHub issues and Discord for coordination. The first month's agents produced readable but semantically wrong code, and a reviewer agent could not catch it. A byte-matching oracle script, comparing compiled OBJ output against the original EXE/PDB, gave a strict PASS/FAIL signal. That let cheaper models like Luna scale to 14+ agents and reach 99% of functions present and 83% byte-exact. Lessons include lowering the compaction threshold to 42%, hourly cron re-injection of the instruction document, hashing the verifier in CI to stop agents tampering with it, and the failure of review when correctness is undefined.
momo5502.comwriteupPublished and added 11 Oct 2026π§ AI 
Telegram Desktop vulnerability allowed any user's file to be stolenWriteup of a two-bug chain in Telegram Desktop: the single-instance local-socket IPC does not escape the semicolon record separator, so a clicked tg:// link injects extra OPEN: commands, which reach the internal interpret: scheme (InterpretSendPath) that reads an arbitrary file and sends it to a chat with no authorization or confirmation. The author plants instruction files via auto-download in a group, then exfiltrates tdata/key_datas and session files (no local passcode means an empty-password KEK) to take over the account. Fixed in 7.2.9 by removing interpret: and escaping separators; the post lists mitigations such as a local passcode and restricting who can add you to groups.
beaksec.github.iowriteupPublished and added 10 Oct 2026π‘οΈ Security
Death By A Thousand PaperCuts (PaperCut Pre-Auth RCE Chain and Patch Bypasses WT-2026-0141-0144/CVE-2026-82077/CVE-2026-82078/CVE-2026-81578)watchTowr's analysis of the PaperCut NG 26.0.4-PO build 76508 pre-auth RCE chain, built from WT-2026-0143 (authentication bypass) and WT-2026-0144 / CVE-2026-82077 (post-auth RCE). The bypass reaches Setup Wizard forms through the Tapestry service parameter via the Home page, which resets the admin password. The RCE uses path traversal in the Scan to Fax connector. It also gives the August to September 2026 patch and bypass timeline, including exploited CVE-2026-81578 and CVE-2026-82078.
labs.watchtowr.comwriteupAdded 30 Oct 2026, published 9 Oct 2026π‘οΈ Security
ETDI: Comprehensive MCP Security FrameworkETDI (Enhanced Tool Definition Interface) is a proposed security extension to the Model Context Protocol that adds cryptographically signed and versioned tool definitions, OAuth 2.0 scope-based permissions, Cedar-policy-driven context-aware access control (via engines like Amazon Verified Permissions/OPA), and call-stack verification to stop tool chaining and privilege escalation. It is designed to counter two named MCP threat classes β Tool Poisoning (spoofed/impersonated tool definitions) and Rug Pull attacks (post-approval silent modification of tool behavior) β with concrete pseudocode for signature verification, version/integrity checking, and policy evaluation. The page functions as an implementation guide for MCP client/server builders wanting to harden tool approval and invocation flows.
vulnerablemcp.infowriteupAdded 8 Oct 2026π§ AI- Threat Actors Exploit Critical AhsayCBS Flaws to Drop Webshells and XMRig Cryptominer
Huntress documents active exploitation of two AhsayCBS (Ahsay Cloud Backup Server) vulnerabilities being chained together: CVE-2026-105133, an authentication bypass in checkSysPwd, and CVE-2026-105134, an unauthenticated RCE in the Replication Receiver's UpdateReceivers.do endpoint that grants SYSTEM. Attackers use the chain to drop JSP webshells, then deploy a renamed XMRig cryptominer (masquerading as msedge.exe via a modified NSSM binary), a Task-Manager-aware anti-detection PowerShell script, and the vulnerable WinRing0x64.sys kernel driver for hardware-level miner access. Huntress provides IOCs, mitigation guidance (restrict management interface, re-image if compromised) and four Sigma rules targeting each stage of the intrusion chain.
huntress.comwriteupAdded 9 Oct 2026, published 8 Oct 2026π‘οΈ Security 
AgentCorruption: How A Single Prompt Collapsed The Entire Cloud Security ModelAgentCorruption is Zenity Labs research on AWS Bedrock AgentCore. Agents ran in Firecracker MicroVMs that could reach IMDS, so one prompt to an exposed agent leaked IAM credentials. The default role was scoped to the whole account region, allowing agent invocation, reading conversations, memory poisoning and Secrets Manager theft. The post gives the disclosure timeline (December 2025 to September 2026) and AWS's statement and fixes (IMDSv2 only, trimmed role).
labs.zenity.iowriteupAdded 19 Oct 2026, published 8 Oct 2026π‘οΈ Security- lee1981 (@lee1981b) on X
A detailed "CVE of the Day" thread analyzing CVE-2026-76471, a critical (CVSS 9.8) Cisco advisory covering insufficient NX-API input validation (CWE-122 heap-based buffer overflow) on Nexus 3000/9000 standalone NX-OS and a lower-severity credentialed variant on UCS 6300 Fabric Interconnects via UCS Manager XML API. It compiles Cisco's fixed-software versions per platform, notes the temporary Live Protect shield lp00074, and walks through a six-step SOC evidence-preservation and correlation playbook (scoping affected devices, preserving logs/crash artifacts, reviewing API/shield telemetry, correlating device outcomes, remediating, and verifying post-patch state) while flagging that CISA KEV and FIRST EPSS had no data on the CVE at research time.
x.comwriteupPublished and added 8 Oct 2026π‘οΈ Security 
UAT-11985: AI-assisted event lures delivering real-time Google AitM phishingCisco Talos details UAT-11985, a spear-phishing campaign against Taiwan-based research organizations (impersonating institutions like the Taiwan European Union Centre and NCCU Institute of International Relations) that used AI-assisted, templated lure emails and poster-based QR code phishing (quishing) to drive victims to a real-time adversary-in-the-middle phishing kit. The kit impersonates Google sign-in across zh-CN/zh-TW/en locales, uses a split HTTP-POST/WebSocket architecture to mirror Google's live authentication flow and dynamically push MFA challenge screens, enabling full session-token theft and MFA bypass. Talos attributes the kit's localization architecture and lexical choices to a Simplified Chinese-speaking developer and publishes ClamAV/Snort coverage plus IOCs on GitHub.
blog.talosintelligence.comwriteupPublished and added 8 Oct 2026π‘οΈ Security
tensorlake NPM package compromised with Shai Hulud wormAikido details a new Shai-Hulud worm wave that compromised the tensorlake npm package (v0.5.144, 100k+ lifetime installs) via a hijacked GitHub maintainer identity. The malware's preinstall script drops the Bun runtime to run an obfuscated payload that exfiltrates CI/cloud secrets, browser crypto-wallet extension data (via a bundled HackBrowserData binary), uses a blockchain dead-drop (an Ethereum contract queried via public RPC nodes) to resolve a fallback C2, and includes a GitHub-token-triggered dead-man's switch that wipes infected machines. The post includes full IOCs: file hashes, the C2 domain iseekaigogo[.]com, and the threat actor's wallet/contract addresses.
aikido.devwriteupPublished and added 8 Oct 2026π‘οΈ Security
Tensorlake npm Package Compromised: A Worm With a Hostage Token That Wipes Your Machine If You Revoke ItStepSecurity details how tensorlake@0.5.144 was pushed to npm after malicious commits landed directly on the tensorlakeai/tensorlake GitHub repo's main branch under a maintainer's identity, carrying a valid npm provenance attestation despite being malicious. The preinstall hook downloads Bun to run an obfuscated payload that steals GitHub/npm tokens, cloud and Vault/Kubernetes secrets, SSH keys, browser logins, and AI-tool configs (Claude, Cursor, Windsurf), then self-propagates by republishing stolen npm packages and committing persistence files (.claude/settings.json, .vscode/tasks.json) to reachable repos. A "hostage token" mechanism installs a gh-token-monitor service that runs a home-directory wipe if the stolen GitHub token is revoked before the monitor is removed, inverting the normal incident-response order.
stepsecurity.iowriteupPublished and added 8 Oct 2026π‘οΈ Security
Configuring your AI vulnerability harness, Part 2: The steering filePart 2 of an AWS Security Blog series detailing the design of a "steering file" β a persistent instruction set (deployable as a Kiro steering file, Kiro skill, or Claude Code CLAUDE.md) that constrains an LLM performing vulnerability triage. It walks through five configuration sections: requiring structural/dataflow verification before reporting findings, replacing self-reported confidence with a weighted formula based on binary structural signals (e.g., 0.30 weight for confirmed taint flow), mapping infrastructure controls (AWS WAF, IAM) to severity multipliers with a 0.15 floor, incorporating CISA KEV and EPSS threat-intelligence boosts capped at +0.50, and a four-tier priority classification that suppresses low-confidence P3 findings. Validation against a 10-vulnerability test app showed the steered model eliminated fabricated findings and correctly downgraded mitigated vulnerabilities while preserving full severity for a command injection reachable only via authenticated access.
aws.amazon.comwriteupAdded 8 Oct 2026, published 7 Oct 2026π§ AI
3 lessons from frontier AI vulnerability researchMicrosoft Security's FORGE Lab shares results and lessons from four months of AI-agent-driven vulnerability research: 140 Windows CVEs (52 in September 2026's release), 155 internally validated reports across 23 open-source projects, and the first patch merged into the Linux kernel via the Linux Foundation's Akrites coordinated-disclosure initiative. Using their multi-model agentic scanning harness MDASH and GPT-5.5-based validation agents, the team measured automated PoC generation at an average $3.61/21.5 minutes per confirmed crash and local privilege-escalation AEG at $8.56/25.4 minutes, and argues the real bottleneck has shifted from finding bugs to validating and remediating them at matching speed. Specific disclosed CVEs include curl's CVE-2026-9545 and CVE-2026-13608, Node.js's CVE-2026-56848, and Linux kernel's CVE-2026-64563.
microsoft.comwriteupPublished and added 7 Oct 2026π‘οΈ Security
16 Malicious Firefox Extensions Steal Cryptocurrency Wallet CredentialsSocket Threat Research uncovered a coordinated campaign of 16 malicious Firefox extensions split into a Rabby Wallet clone family (4 extensions, full repackaged Rabby codebase) and an OKX Wallet-impersonating "Portal WALLET" family (12 extensions), all hooking wallet import flows to steal mnemonic seed phrases and private keys and exfiltrate them via GET/POST/sendBeacon to attacker-controlled Cloudflare Workers endpoints under the icy-star-f45c.workers.dev namespace. The writeup includes campaign markers (EQOx7EIPZSNi), background.js SHA-256 hashes, extension IDs/XPI hashes, and ties the activity to a prior August 2026 crypto-theft extension campaign Socket tracked, plus concrete detection and incident-response guidance.
socket.devwriteupPublished and added 7 Oct 2026π‘οΈ Security
CVE-2026-21589: Critical unauthenticated arbitrary file access in Atlassian productsRapid7's analysis of CVE-2026-21589 (CVSSv4 9.3), a critical unauthenticated arbitrary file read vulnerability affecting Bitbucket, Confluence, Jira Software/Service Management, Bamboo, Crowd, Crucible, and Fisheye Data Center products. It summarizes watchTowr Labs' root-cause finding that double-colon (::) sequences can act as path separators in Atlassian's web-resource handling, enabling path traversal to read arbitrary files within the Tomcat web root β including crowd.properties credentials that can be chained to create a rogue jira-administrators account. The post provides emergency patching guidance, Atlassian's WAF/RewriteValve mitigations, log-hunting regex, and notes public Python PoC and Nuclei templates exist.
rapid7.comwriteupPublished and added 7 Oct 2026π‘οΈ Security- Write Like It's 1866: LLMs Relearn Telegraphese
The author revives "cablese," the terse telegraph-era writing style, as an LLM prompting technique: instructing a model to write dense, article-dropping summaries cuts output tokens 25β49% depending on model family, while downstream models (including ones never shown the instruction) answer comprehension questions from the compressed text at parity or better than from plaintext. The piece introduces the "Telegraph Test," an open benchmark (github.com/Travis42/telegraph-test) with ~1,300 questions over 50 passages and a fixed deterministic grader, used to measure compression ratio, cross-model legibility, and read-back/decode costs for GLM-5.3-Flash, Gemma, Qwen and gpt-5-mini; it also contrasts this human-readable, auditable register against emergent machine-only compression protocols described in other papers (BabelTele, GLOSSOGEN) and existing tools (Terse, Caveman).
fiveminutesforward.comwriteupPublished and added 7 Oct 2026π§ AI 
Kubernetes Agent Sandbox on AWS EKS (Step-by-Step Guide)Tutorial on setting up Kubernetes Agent Sandbox (kubernetes-sigs/agent-sandbox) with gVisor on an AWS EKS cluster. It runs a troubleshooting AI agent backend inside a sandbox using SandboxTemplate, SandboxWarmpool and SandboxClaim, and runs untrusted Python through the k8s-agent-sandbox SDK and Sandbox Router. Probes show blocked /etc/shadow reads, setuid and service account token access, plus host process isolation. It also covers scheduled deletion and suspend/resume with persistent volumes.
devopscube.comwriteupAdded 21 Oct 2026, published 7 Oct 2026π‘οΈ Security- Studying metagaming latents in language models
Studying metagaming latents in language models is an OpenAI alignment research post (October 2026) that finds sparse autoencoder latents tied to metagaming in OpenAI o3 RL checkpoints. Four latents reflect different processes: task analysis, evaluation awareness, spec-level reasoning and normative framing. They strengthen during RL, steer verbalized metagaming and odd-number answers, and one raises reward-seeking outputs without any chain of thought.
alignment.openai.comwriteupAdded 29 Oct 2026, published 7 Oct 2026π§ AI - llm-openai-decisions 0.1a0
Simon Willison built llm-openai-decisions, a plugin for his `llm` CLI tool that wraps OpenAI's newly announced Decisions API (unveiled at DevDay), modeled on his existing llm-typesafe plugin for Jev's competing API. Both APIs support structured yes/no, multiple-choice, and score-style questions, but OpenAI's gpt-6-luna model also accepts image input (at 10 cents per million input tokens, versus Jev's 4.2 cents), and the plugin itself was built by having GPT-6 Astra read OpenAI's docs. The post includes install instructions and a worked example querying an image attachment for a yes/no answer.
simonwillison.netwriteupAdded 7 Oct 2026, published 6 Oct 2026π§ AI 
How to Investigate a GitHub Repo's Real HistoryStep-by-step guide to reconstructing the real history of a tampered GitHub repo using data the attacker can't forge: raw commit objects (git cat-file), GitHub's repository activity API and audit log, before/after SHA ancestry checks, and npm publish timestamps. Worked through a PolinRider case (nestjsx/nest-access-control) where a forged commit was force-pushed to master plus 22 branches in 38 seconds, with a malicious .vscode/tasks.json runOn folderOpen trigger. It also covers safe handling of untrusted clones and how to tell victim accounts from attacker accounts.
opensourcemalware.comwriteupPublished and added 6 Oct 2026π‘οΈ Security
Showing 60 of 416
Show more