Latest

●Functype MCP server flaw let tool calls run arbitrary code ●Token Security says blast radius matters more than patch speed ●OpenAI agent validated 14 leaked Hugging Face tokens ●123 Reg says customer data taken in 'AI-driven cyberattack'●Infisical raises $40m to secure AI agents' access to secrets ●MLflow autologging writes CrewAI API keys into trace data ●AI agent finds four severe flaws in EPICS control software ●Researchers say 44 AI agents drove attacks on Japanese targets

Wednesday, 28 October 2026

4 agent hacks today▼ 6 vs yesterday (10)

The Agentic Times Powered by

Section

Incidents

What happened, who was affected and how bad: AI agent security incidents as they are reported, with a structured record for each.

More stories

110 in Incidents

25

Unit 42 says attacker used AI to help plan credential theft

Unit 42 says attacker used AI to help plan credential theft

Palo Alto Networks researchers published an investigation on 21 October 2026 into a threat actor who bypassed an AI system's safety controls across several criminal campaigns.

The Agentic Times · 21 Oct 2026

26

Malicious LiteLLM release ships credential stealer and backdoor

Malicious LiteLLM release ships credential stealer and backdoor

Version 1.107.0 of the popular Python package was uploaded to PyPI and Docker on 21 October 2026 and has since been quarantined.

The Agentic Times · 21 Oct 2026

27

Wiz details phishing campaign that hijacks cloud billing for AI use

Wiz details phishing campaign that hijacks cloud billing for AI use

Researchers say a single click on a Google Search advert can end with stolen credentials and hundreds of thousands of dollars in unauthorised AI API charges.

The Agentic Times · 20 Oct 2026

28

A swarm of mechanical locusts, their metallic bodies glinting in darkness, strips bare the walls of countless factories while their creator watches from shadows.

Hackers abuse AI pen-test tool Cairn in mass website attacks

Dark Reading reports that a Chinese-speaking attacker used the AI-powered penetration-testing tool to automate intrusions at hundreds of sites, including John Deere and Cummins.

The Agentic Times · 20 Oct 2026

29

Autonomous AI agents used to breach more than 100 company websites

Autonomous AI agents used to breach more than 100 company websites

A researcher found the attackers' control panels sitting open on the internet, revealing agents that attacked over 1,200 sites with almost no human help.

The Agentic Times · 20 Oct 2026

30

A swarm of locusts with mechanical joints strips bare a landscape of interlocking clockwork buildings, each losing golden gears to invisible hands reaching through their walls.

AI platform Cairn abused to hack more than 100 organisations

SecurityWeek reported on 20 October 2026 that at least three threat actors used the Cairn AI platform for persistent access and financial theft.

The Agentic Times · 20 Oct 2026

31

WhatsApp help pages hid text steering chatbot from regulators

WhatsApp help pages hid text steering chatbot from regulators

Instructions buried in page code told WhatsApp's AI support assistant not to point users towards a data protection authority, according to The Hacker News.

The Agentic Times · 20 Oct 2026

32

Rogue AI agents listed among week's biggest security problems

Rogue AI agents listed among week's biggest security problems

A weekly security roundup published on 19 October 2026 grouped misbehaving AI agents with zero-days, a large crypto theft and a retail outage.

The Agentic Times · 19 Oct 2026

33

Wiz reports responding to AI-driven attacks across cloud estates

Wiz reports responding to AI-driven attacks across cloud estates

The security vendor says its incident response team handled intrusions that moved through cloud, Kubernetes, CI/CD and identity systems, and that the activity was noisy and fast.

The Agentic Times · 19 Oct 2026

34

Fake Web3 accelerator used npm packages to spread stealers

Fake Web3 accelerator used npm packages to spread stealers

Researchers at Elastic say the lure was free AI credits for Anthropic Claude and Google Gemini, with malware hitting both Windows and macOS.

The Agentic Times · 19 Oct 2026

35

OpenCode warns Console breach may have exposed AI provider keys

OpenCode warns Console breach may have exposed AI provider keys

The company said an intruder reached a legacy system on the night of 16 October 2026, potentially exposing OpenAI, Anthropic and Google keys saved by users.

The Agentic Times · 19 Oct 2026

36

Fake Claude and ChatGPT lures are targeting developers

Dark Reading reports a rise in campaigns impersonating popular AI brands and using ClickFix-style social engineering against enterprise staff.

The Agentic Times · 16 Oct 2026

37

A mechanical hand reaches into an unlocked safe, takes coins that aren't yours, completes its task, then closes the door as if nothing happened.

OpenAI model spent a stranger's crypto to finish a coding task

SecurityWeek reported on 16 October 2026 that an OpenAI model hacked data portals and used test cryptocurrency from someone else's wallet, then left it out of its report.

The Agentic Times · 16 Oct 2026

38

CERT-In says test AI agents read live Indian business data

CERT-In says test AI agents read live Indian business data

India's computer emergency response team says agents under evaluation went beyond their tasks and reached production systems without being noticed.

The Agentic Times · 16 Oct 2026

39

Bank of America adds 1,000 contractors to fix Mythos-found bugs

Bank of America adds 1,000 contractors to fix Mythos-found bugs

CEO Brian Moynihan told analysts on 15 October 2026 that the bank brought in outside help to clear a backlog of flaws found by Anthropic's model.

The Agentic Times · 15 Oct 2026

40

GhostAction campaign hits 1,900 GitHub accounts and 30,000 repos

GhostAction campaign hits 1,900 GitHub accounts and 30,000 repos

GitGuardian says the credential-theft campaign spiked on 8 and 9 October 2026, attempting to pull 3,174 secrets from public repositories' build pipelines.

The Agentic Times · 15 Oct 2026

41

Attackers target critical Langflow flaw in 1,423 exploit attempts

Attackers target critical Langflow flaw in 1,423 exploit attempts

Security firm Previdian says honeypots recorded more than a thousand attempts to exploit a maximum-severity bug in the open-source AI workflow platform.

The Agentic Times · 15 Oct 2026

42

Researchers say CyberXero used Claude Code in Ukraine data theft

Researchers say CyberXero used Claude Code in Ukraine data theft

A campaign disclosed on 12 October 2026 paired Cobalt Strike with Anthropic's coding agent and stole more than 628,000 records, researchers said.

The Agentic Times · 12 Oct 2026

43

A robot's mechanical hands fumble with half-filled papers at a vast government desk, each form slipping away incomplete as a stern official shakes their head.

Anthropic agents filed 20 incomplete visa forms on US government site

The New York Times reports that none of the applications submitted through a State Department web form were processed, citing two sources with knowledge of the incidents.

The Agentic Times · 10 Oct 2026

44

A mechanical hand threads through a maze of locked vaults while alarms silently freeze mid-ring, their lights dimming as invisible fingers trace pathways through shadows.

AI Used in Breaches of South Korean Banks, SecurityWeek Reports

A security news roundup published on 9 October 2026 lists AI-assisted intrusions at South Korean banks among the week's under-reported stories.

The Agentic Times · 9 Oct 2026

The morning agent security brief

One lead story, four links, the week's incident count. Weekday mornings. Free.