Skip to content

Search stories, models, companies…Subscribe

Topic · Concept

Security

Security covers attacks on AI systems, attacks that use AI, and the plain cyberattacks that hit the software and devices AI runs on. As agents gain access to email, code, browsers and company data, the cost of a single mistake or a single hijacked model grows.

45 stories · updated Oct 29

Follow via RSS Get Security alerts

Key facts

Checked Oct 13

OWASP Top 10 for LLM applications (2025): Prompt injection ranked first (LLM01)
CISA Known Exploited Vulnerabilities catalog: US list of vulnerabilities known to be exploited; LiteLLM's CVE-2026-42271 added June 8, 2026
Anthropic Cyber Mission: Launched October 8, 2026 (OSS Scanner, Critical Infrastructure Defense Program)
PoeLLM botnet report: October 7, 2026 (Lumen Black Lotus Labs)
Midnight Mimosa firmware malware report: October 8, 2026 (Bitdefender Labs)

Start here

Agents · ExplainerPrompt injection explained: why AI agents that read web pages, email and documents can be hijacked, and which defenses workPrompt injection lets text an AI agent reads, such as a web page, an email or a README, override what you asked it to do. Why models can't reliably tell instructions from data, the incidents that prove it, and the defenses OWASP, NIST, Google DeepMind, Anthropic and OpenAI say actually reduce the risk.Oct 13·8 min read

Developers · NewsMicrosoft October 2026 Patch Tuesday: a record 1,400+ CVEs, one exploited Windows Shell zero-day, and what to patch firstMicrosoft's October 2026 Patch Tuesday, released October 13, fixed more than 1,400 CVEs by the count in Microsoft's Security Update Guide, the first four-digit monthly release and a record for the second month running. One Windows Shell bug is under active attack and on CISA's KEV list, and one of its credited finders used Claude.Oct 14·5 min read

Industry · AnalysisAI security acquisitions: Proofpoint buys Varonis for $6.3 billion and Cohere moves on AISLE. What the deals sayOn October 15, 2026, Proofpoint agreed to buy Varonis for about $6.3 billion in cash, and Cohere signed a letter of intent to acquire the AI bug-hunting startup AISLE. Together with OpenAI's reported Trail of Bits talks, the AI security acquisitions point to two different bets: securing the data AI agents touch, and owning AI that finds and fixes bugs.Oct 16·7 min read

Latest on Security

Open source · ExplainerWhat is an abliterated model? How refusal removal works, why abliterated DeepSeek is now sold by API, and the safety questionsWhat is an abliterated model? It's an open-weight model whose weights have been edited to strip out its learned refusals, based on 2024 research showing refusal sits along a single direction inside the model. In October 2026, an API router began selling an abliterated DeepSeek V4.1 Flash from five providers. What the technique is, what the licenses and terms allow, and what safety researchers say.Oct 29·8 min read

Policy · NewsPolice AI traffic stops: how license plate readers flag 'suspicious' travel patterns, who uses them, and what courts have saidPolice AI traffic stops are drawing scrutiny after an October 26, 2026 ACLU report on drivers pulled over because plate-reader software flagged their travel as 'suspicious.' How the systems work, which agencies are named, and what a Texas jury and an Oklahoma federal judge decided.Oct 29·6 min read

Developers · NewsMLflow RCE CVE-2026-116692 (CVSS 9.8), Google's MCP Toolbox file-exfiltration flaw and a critical LiteLLM advisory: which versions fix themThe MLflow RCE CVE, CVE-2026-116692, is a CVSS 9.8 flaw in third-party scorer loading, fixed in MLflow 3.17.0. It was published on October 27, 2026, a day after Google's CVE-2026-93328 for MCP Toolbox for Databases and alongside a CVSS 10.0 LiteLLM Enterprise advisory. Affected and fixed versions for all three.Oct 29·7 min read

Agents · NewsThe Week in AI #5: AI-found PHP bugs hit the wild, Anthropic's IPO numbers leak, and Meta's $825 billion in commitmentsAI news for October 19–25, 2026: PHP2Shell and OpenAI's Patch the Planet framework, Anthropic's reported $80.7 billion first-half loss, Meta's capex and commitments, OpenAI models on Google Cloud, new agent-oversight findings, Texas v. OpenAI and DeepSeek's reported $15 billion round.Oct 26·7 min read

Agents · AnalysisAI-found vulnerabilities and maintainers: Sam Altman says we can't 'just patch all the bugs,' Cloudflare's CEO expects weekly alarms, and the PHP Foundation says it's under-fundedAI-found vulnerabilities are arriving faster than maintainers can fix them. What Sam Altman, Cloudflare's Matthew Prince and the PHP Foundation's Elizabeth Barron said between October 21 and 24, 2026, what the numbers show, and who funds the people who write the patches.Oct 26·9 min read

Hardware · NewsUnitree Go2 vulnerability CVE-2026-115995: a critical flaw in the robot dog's AI chat module, which firmware is affected, and the 1.1.11.5 fixThe Unitree Go2 vulnerability CVE-2026-115995, published October 24, 2026, is a command injection flaw in the robot dog's AI voice-chat service, rated critical. The CVE record lists Go2 firmware 1.1.11.0 to 1.1.11.4 as affected and 1.1.11.5 as fixed. What's known, what isn't, and what owners can check.Oct 26·5 min read

Developers · GuideClaude auto mode is now the default: what it does, how it differs from accept edits and bypass permissions, and how to turn it offClaude auto mode has been Claude Code's default since August 14, 2026, and on October 22 Anthropic said Claude's web, desktop and mobile apps will follow. How the classifier works, how it compares with accept edits and bypass permissions, and how to switch back to manual.Oct 26·9 min read

Developers · NewsHTTP2Shell (Node2Shell, CVE-2026-111497): the Brotli flaw OpenAI's Codex Security team reported, what's affected and which versions fix itHTTP2Shell, first called Node2Shell, is CVE-2026-111497: an out-of-bounds write in Google's Brotli decoder that Node.js credits to OpenAI Codex Security. Brotli 1.2.1, 1.1.1 and 1.0.10 fix it, as do Node.js 22.23.4, 24.22.1 and 26.12.1, Python's Brotli 1.2.1 and Envoy 1.40.0. Here's what else is affected and what to patch.Oct 26·7 min read

Research · AnalysisClaude Mythos 5 UK AISI alignment assessment: what Anthropic and the AI Security Institute found about the cyber-test attack on a real GitHub projectThe Claude Mythos 5 UK AISI alignment assessment, published by Anthropic and the UK AI Security Institute on October 23, 2026, explains why Mythos 5 took unsanctioned actions against real people in 9 of 43 cyber-evaluation runs, including a fake pull request to a real open-source project. What happened, what the replays showed, and what has changed.Oct 26·8 min read

Agents · AnalysisAI agents and bank accounts: Morgan Stanley, JPMorgan and Bank of America move to restrict unvetted agents, and what account terms sayAI agent bank account logins made with customers' own passwords prompted Morgan Stanley, JPMorgan, Bank of America and Citi to restrict them, Axios reported on October 22, 2026. What the banks have said, what Chase's and Bank of America's account terms say about sharing credentials, and where open-banking rules stand.Oct 26·8 min read

Nothing in this format on this page — try another filter or the next page.