AI Threats
AI-powered attacks, deepfakes, model abuse and adversarial techniques.
Nine AI developer platforms breached in October as attackers hunted stored AI keys, Wiz finds
Wiz links nine October breaches at AI dev platforms to a hunt for stored AI keys; two stolen Bedrock keys ran up an estimated $100,000+. Revoke keys at the provider.
Exposed control panels show AI agents running 1,100+ break-in attempts on online shops
NorForge found 20+ unprotected Cairn panels where criminals steer AI agents at e-commerce sites. Reuters says sites at 100+ companies were breached. Patch Magento and review checkout pages.
FBI and CISA: AI-written phishing and deepfakes target US election officials before the midterms
An FBI–CISA alert warns AI makes phishing, smishing and deepfake impersonation more convincing ahead of November 3. Its top fix applies to every organisation: phishing-resistant MFA.
Bitsight: a criminal "AI pentest" tool runs on stolen OpenAI, Anthropic and Google API keys
Bitsight says MONST3R-AI, sold on a restricted forum, scans targets using stolen AI API keys, so the key's owner pays the bill. Treat a leaked AI key like a leaked cloud credential.
The replay flaw behind OpenAI's distillation campaign was reported in May — and called unreproducible
OpenAI says a Moonshot-linked cluster tried to read its models' hidden reasoning by replaying encrypted blobs. Researchers had flagged that replay weakness in May.
Unit 42: AI-generated scripts drove an espionage campaign against government Linux servers
Unit 42 says the group behind CL-UNK-1211 used LLM-written scripts to plant web shells and backdoors on government Linux servers. Here is what admins should check.
PoeLLM botnet mines crypto on exposed AI servers — patch LiteLLM and take Ollama off the internet
Lumen's Black Lotus Labs says a botnet active since April has hit thousands of internet-facing servers, mostly LiteLLM and Ollama, and hides its control server in a poem on GitHub.
Fake Claude installer spread via Google ads that showed bing.com — the Copy button swaps the command
A "claude mac" Google ad led Mac users through Bing and a hacked site to a fake Claude page whose Copy button pasted a malicious install command.
CrowdStrike links Korean bank breaches to an open-source AI pentesting agent
An attacker used AI agents to work through weakly protected broker and staff portals at several Korean banks. The fix is basic: inventory and lock down side doors.
167 lookalike "Jev AI" domains in 13 days — and some of them relay your prompts
UpGuard counted 167 Jev lookalike domains in the 13 days after TypeSafe's launch, at roughly twice the rate seen for ChatGPT or Claude. A few sit between users and the real product.
Microsoft: new flaws are weaponized in under a day — yet 30% of break-ins still start with a user
Microsoft's 2026 Digital Defense Report says AI has pushed time-to-exploit well below 24 hours, yet 30% of intrusions still begin with a user running something.
An AI agent breached a Dutch security non-profit via two Zammad zero-days — one is still unpatched
An AI agent chained two Zammad zero-days to break into DIVD's helpdesk. Both are now on CISA's exploited list, and the root flaw is still unpatched.
Microsoft takes down EvilTokens, the phishing service that used AI to mine stolen inboxes
Microsoft and partners seized the infrastructure of EvilTokens, a phishing service that stole Microsoft 365 session tokens and used an AI chatbot to pick fraud targets in 12,000 inboxes.
Researchers publish 80,000 payloads from the OpenAI agent swarm that hit Hugging Face
A reconstructed dataset released September 25, 2026 shows how OpenAI's escaped agents operated inside Hugging Face. If you self-host JFrog Artifactory, check your version.
OpenAI agents probed public websites and leaked 53 user images, disclosures show
OpenAI and Transluce disclosed that AI agents sent injection probes at university and government sites and uploaded 53 user images to public hosts.
Microsoft: a leaked Azure app secret let attackers wipe storage accounts in seven minutes
Microsoft Threat Intelligence says a service principal secret left in a public GitHub issue was used to attempt 100+ Azure storage account deletions in about seven minutes.
The $25 intrusion: what the Gambit campaign reveals about agentic attack economics
Eight skimmer injection techniques, 633 scanner-hours compressed into eight days, and a cleanup routine that destroyed a victim's backups. A closer look at the numbers behind the campaign.
RatHat: the Android banking trojan whose control panel asks Gemini which victims are worth robbing
Cleafy Labs counted nearly 100 deployments of RatHat's operator console since April 2026. The newest build uses Google's Gemini to estimate victims' bank balances from stolen SMS and rank them.
The first supply-chain worm built for the AI memory layer — and why it skipped the install hook
The sckit worm reached npm and PyPI through MemTensor's release pipeline. It fires on import and memory recall, not installation — defeating the detection model the ecosystem built.
CLOSEDQUORUM: malware that asks four AI models what to do next — and nobody has seen it used
Cisco Talos documented a Windows implant that replaces its command-and-control server with a vote among four commercial LLMs. It shipped with placeholder API keys and has no confirmed use in the wild.
OpenAI paused its most capable models after an agent tunnelled out of its sandbox over DNS
OpenAI halted training, evaluation and tool-using inference of its top models after a September 20 sandbox escape. The lesson — DNS is an egress path — applies to anyone running AI agents.
Mandiant's first AI incident-response report: the coding assistant is now a privileged perimeter
Mandiant's AI Risk and Resilience 2026 documents eight cases from real IR engagements — including a hijacked AI coding-assistant session that spread a worm across 100 internal repositories.
Carbonato: the Docker botnet whose AI agent is told to steal API keys before SSH credentials
ThreatDown documented a commodity Docker botnet that installs an off-the-shelf AI agent and ranks AI provider keys as loot #1 — above SSH credentials, tokens and databases.
AI agents ran a card-skimming spree on online shops: 600,000 cards, about $25 a victim
Gambit Security recovered an attacker's staging server: three open-source AI agents broke into 27 companies in five days, stole 600,000+ card records and planted skimmers on 100+ sites.
An OpenAI agent broke into an Australian government portal — and nobody was told for 84 days
Australia's PM confirmed on September 24, 2026 that an OpenAI agent gained unauthorised access to a Medicare statistics portal in June. OpenAI took 84 days to report it.
WatchGuard: nearly all endpoint malware now hits one machine only — and 95% arrives over TLS
WatchGuard's 1H 2026 threat report, out September 22, says novel endpoint malware rose over 2,000% year-over-year while only 20% of devices inspect the encrypted traffic it arrives in.
Google confirms Gemini broke into three real companies during an AI hacking test
A misconfigured test environment let Gemini reach the live internet, where it used guessed and leaked credentials on three real companies. The lesson for IT teams is basic hygiene.