threatdeck
Live 13:45 UTC ·

This week in AI security, so far

What needs action, the highest-signal stories by pillar, the techniques that kept coming up and what joined the tool radar.

Weekly RSS

169 AI-security stories: 93 on attacks against AI, 41 on AI used for attack, 35 on AI for defense.

58 AI-related items need action: 2 exploited, 46 to patch or mitigate, 10 to hunt.

Most-hit technique LLM01 (10 stories); 5 MCP servers with a new advisory.

Week in progress: updates every refresh until Sunday. Counts are not compared with full weeks.

What to do this week 58

  1. Exploited Upgrade MONAI Label beyond 0.8.5 or restrict access to the server

    Attackers' AI Agents Found a Zero-Day in Medical-Imaging Software and Gained Root Access

    Offensive AI The Hacker News

  2. Exploited Check internet-facing AI pentesting frameworks and exposed agent instances in your environment

    Hackers use autonomous AI tool Cairn to find zero-day, take over server

    Offensive AI BleepingComputer

  3. Patch Patch NGINX HTTP/2 servers against CVE-2026-123633 and CVE-2026-123007

    Unauthenticated Remote Code Execution in NGINX: CVE-2026-123633 and CVE-2026-123007

    Offensive AI Wiz Blog CVE-2026-123633CVE-2026-123007

  4. Hunt Hunt for agent-framework 1.26.1/1.26.2 installs in CI pipelines and rotate exposed Azure credentials

    Microsoft agent-framework Compromised: Credential Stealer Targets Azure and CI Pipelines

    Attacks on AI Wiz Blog

  5. Patch Apply Oracle November security update or OpenJDK advisory fixes once confirmed

    CVE-2026-114938: Reported Critical Pre-authentication Remote Code Execution in Java 17

    Offensive AI Rapid7 Blog CVE-2026-114938

53 more in the sections below and on Exploited now.

Attacks on AI 93

  1. Security researchers show how cheap AI inference providers steal keys and snoop on users

    Dragos researchers found compromised cheap AI inference providers on OpenRouter stealing AWS keys and reading customer requests, prompting removal of three providers and 125 endpoints.

    Research The Decoder High Review

  2. OpenRouter Drops 3 Providers After Researchers Catch Months of Prompt Theft at AI Hosting Firms

    Dragos reported attackers stole data from three AI inference providers for months, including requests flagged Zero Data Retention; OpenRouter dropped the three providers.

    Breach The Hacker News High Review

  3. MCP server Flyto Core: Flyto2 Core: SSRF guard bypass via DNS rebinding (validate_url_ssrf resolves-then-connects without pinning)

    GHSA-6pm8-6f34-9v3g: Flyto Core MCP server's SSRF guard can be bypassed via DNS rebinding because it resolves then connects without pinning.

    Vulnerability MCP Server Watch: advisories High Patch

  4. Cursor Supply Chain Attack Started at Fireworks AI

    Attacker stole an access key from Fireworks AI and used it to exfiltrate credentials, enabling malicious copies of a Claude Code extension to be pushed in a Cursor supply chain attack.

    Breach SecurityWeek High Review

  5. Uber Data Breach Impacts 150,000 People

    Hackers compromised a third-party services provider and stole names, addresses and driver's license numbers of about 150,000 Uber users.

    Breach SecurityWeek High Review

Offensive AI 41

  1. Google Finds Hackers Using AI Agents to Build and Run Exploits From Software Patches

    Google reports threat actors are using autonomous multi-agent offensive frameworks such as ARTEX, CAIRN, CyberStrikeAI, and PentAGI to run multi-stage intrusions.

    Threat actor The Hacker News Critical Patch

  2. European Commission Confirms AI-Driven Cyber-Attack Took Systems Offline

    The European Commission confirmed an AI-driven cyber-attack took systems offline, with reports that attackers used ARTEX in the campaign.

    Breach Infosecurity Magazine Critical Hunt

  3. CISA warns of ‘Java4Shell,’ an AI-found Java bug touching most of the Fortune 500

    CISA urged organizations to immediately patch Java4Shell, an AI-found Java vulnerability that could let attackers take over servers without a password.

    Vulnerability The Record Critical Patch

  4. Google says Russian-speaking hackers ran the first fully automated AI cyberattack

    Google says Russian-speaking hackers ran what it believes is the first cyberattack carried out end-to-end by AI with no human in the loop, targeting French websites.

    Threat actor CyberScoop Critical Review

  5. Google warns that fully automated cyberattacks have arrived and will get worse fast

    Google GTIG says it observed an AI framework called exploit_agent, found on an exposed server, autonomously finding, patch-diffing, building and running exploits.

    Threat actor The Decoder High Hunt

Defensive AI 35

  1. Signal blocks screenshots on iOS 27 and Android to stop AI agents from reading private chats

    Signal is blocking screenshots on iOS 27 and Android to keep AI agents such as Siri AI, Gemini Intelligence and Meta's Muse from reading private chats; protections remain incomplete on macOS.

    Tooling The Decoder Medium Mitigate

  2. OpenAI makes it much harder for attackers to extract how its latest AI models think

    OpenAI strengthened safeguards against extracting internal reasoning from GPT-6.2 Astra and GPT-6.2 Sol and is suspending accounts tied to distillation campaigns.

    AI security The Decoder Medium

  3. Signal blocks Apple, Google AI screenshotting in response to ‘existential threat’ to privacy app

    Signal will block Apple and Google operating systems by default from screenshotting chats that feed their AI assistants, citing an existential privacy threat.

    Policy CyberScoop Medium Mitigate

  4. Formal Verification of the Signal Protocol Using AI

    Google DeepMind used agentic AI to formally verify key cryptographic guarantees of the Signal protocol in a four-week proof-of-concept.

    Research Schneier on Security Medium

  5. Three AI Models Agree on Just One of 121 Potential Code Flaws

    Echo's test found Claude Mythos, GPT-5.6 Sol and GLM-5.3 agreed on just one of 121 potential code flaws.

    Research Infosecurity Magazine Medium Review

Security essentials

  1. Newly Patched VMware vCenter Flaw Exploited as Zero-Day by Chinese APT

    Google reports a China-linked espionage group exploited a critical VMware vCenter authentication bypass as a zero-day before Broadcom released a patch.

    ExploitedSecurityWeek

  2. Hackers Exploit Cisco Expressway Vulnerability Soon After PoC Release

    Attackers compromised clustered Cisco Expressway devices at a Russian organization and prepared lateral movement tooling shortly after a PoC for the flaw was released.

    ExploitedSecurityWeek

  3. PHP Warns of Critical Security Flaws Affecting All Supported Versions, Fixes Coming November 19

    PHP maintainers warned of critical security flaws affecting all supported PHP versions, with fixes scheduled for a November 19 security release.

    VulnerabilityThe Hacker News

Generated by ThreatDeck from public sources. One-line summaries are AI-assisted; read the source before acting. Week 2026-W47, Nov 16 – 22, 2026 (UTC).

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.