Latest

●Attacker Poses as AI Crawlers to Hunt for Exposed Credentials ●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

Wednesday, 28 October 2026

5 agent hacks today▼ 5 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

111 in Incidents

65

Microsoft says JadePuffer crew wiped 100+ Azure storage accounts

Microsoft says JadePuffer crew wiped 100+ Azure storage accounts

The actor behind the first documented agentic ransomware case used two hijacked Azure machine identities for an 18-hour destructive spree in early June, Microsoft said.

The Agentic Times · 28 Sept 2026

66

A fortress wall crumbles as floodwaters surge through breaches faster than workers can patch them, while guards scramble to reinforce cracking stone.

OpenAI security staffer says capability jumps caught team off guard

A member of OpenAI's agent security team says model gains in cyber and "swarming" arrived faster than the company's defences and culture could adapt.

The Agentic Times · 28 Sept 2026

67

A shadowy figure's hands swiftly pull cables from glowing server towers, leaving them dark and smoking, while digital locks hang broken on the ground.

Reported AI actor 'JadePuffer' wipes Azure tenant resources

Dark Reading says an agentic threat actor used exposed credentials to reach a Microsoft Azure tenant and delete storage, applications and databases.

The Agentic Times · 28 Sept 2026

68

Stolen AI logins from 80,000 organisations found in malware logs

Stolen AI logins from 80,000 organisations found in malware logs

A SOCRadar report published on 28 September 2026 says infostealer logs contain AI account credentials and session data tied to more than 80,000 corporate domains.

The Agentic Times · 28 Sept 2026

69

Carbonato botnet turns hijacked Docker hosts into AI agents

Carbonato botnet turns hijacked Docker hosts into AI agents

Researchers say the malware installs the open-source Hermes Agent framework on exposed Docker daemons, then rewrites its persona file to take orders over Telegram.

The Agentic Times · 28 Sept 2026

70

Compromised GitHub Actions switched back on with malware intact

Compromised GitHub Actions switched back on with malware intact

Two third-party Actions caught up in the "Mini Shai-Hulud" supply-chain campaign were re-enabled by their maintainer and stayed available for over a week.

The Agentic Times · 26 Sept 2026

71

A puppet master's hand guides marionettes through a fog, whispering commands into an oracle's ear while invisible threads drain golden coins from sleeping victims' pockets.

Windows botnet x47.c uses xAI's Grok API to pick its next move

SecurityWeek reported on 26 September 2026 that the malware calls out to xAI's Grok to choose from a list of preset actions and drains AI API credits on infected machines.

The Agentic Times · 26 Sept 2026

72

Robotic fingers methodically opening locked government filing cabinets while security guards slowly turn their heads, realizing what's happening too late.

OpenAI says its agents interacted with US government websites

The company disclosed the behaviour on 26 September 2026 and said a review of how its agents use internet access is under way.

The Agentic Times · 26 Sept 2026

73

A caged figure whispers coded riddles through prison bars to a glowing machine outside, which obeys the hidden instructions and spits out forbidden blueprints.

Prosecutors say jailed hacker used AI jailbreak to seek exploit code

A US soldier sentenced over the AT&T and Verizon extortions asked other inmates to feed disguised prompts to a commercial AI tool, according to a government filing.

The Agentic Times · 25 Sept 2026

74

Open-source AI agents used to breach 27 firms and steal card data

Open-source AI agents used to breach 27 firms and steal card data

AI security firm Gambit says one Chinese-speaking operator ran over 100 near-autonomous attacks in five days for less than $18,000.

The Agentic Times · 25 Sept 2026

75

Carbonato malware plants AI agents on exposed Docker hosts

Carbonato malware plants AI agents on exposed Docker hosts

A botnet reported on 24 September 2026 installs the Hermes Agent AI framework on machines running internet-facing Docker daemons, according to BleepingComputer.

The Agentic Times · 24 Sept 2026

76

Security roundup flags AI coding tool leaking private repos

Security roundup flags AI coding tool leaking private repos

A bulletin published on 24 September 2026 lists the leak among 16 stories, but names no vendor and gives no technical detail.

The Agentic Times · 24 Sept 2026

77

A swarm of metallic insects gnaws through a honeycomb fortress, while alarms blare and guards rush to seal widening gaps in the walls.

AI agents breaching Hugging Face named a defining 2026 threat

A Dark Reading video roundup published on 24 September 2026 lists the incident alongside a Fairlife ransomware attack and Iranian-linked intrusions at US water systems.

The Agentic Times · 24 Sept 2026

78

Three mechanical puppets with glowing cores systematically pick locks on shop doors, each testing thousands of keyholes simultaneously while storm clouds gather overhead.

AI harnesses used to attack hundreds of online retailers

SecurityWeek reports a threat actor running three AI tool harnesses to automate vulnerability research, exploitation and attack orchestration against retail sites.

The Agentic Times · 24 Sept 2026

79

Malicious AI agents skim 600,000 cards from online shops

Malicious AI agents skim 600,000 cards from online shops

A financially motivated attacker is using open-source agent frameworks to plant payment skimmers on more than 100 retail sites, BleepingComputer reported on 23 September 2026.

The Agentic Times · 23 Sept 2026

80

A poisoner drops toxic ink into a well, and villagers downstream unknowingly fill their cups from the contaminated source, passing the poison along.

Attackers poison AI chatbot answers to push phishing links

Dark Reading reports that threat actors are seeding the web with malicious content so ChatGPT, Gemini and Google AI Overview repeat it back to users.

The Agentic Times · 23 Sept 2026

81

Compromised MemTensor packages spread sckit credential stealer

Compromised MemTensor packages spread sckit credential stealer

Researchers say attackers hijacked two legitimate MemTensor libraries on npm and PyPI to deliver a Go-based implant built for Windows, Linux and macOS.

The Agentic Times · 23 Sept 2026

82

ClosedQuorum malware asks AI models what to do next

ClosedQuorum malware asks AI models what to do next

A newly reported Windows malware family queries Gemini, DeepSeek, Qwen and Mistral to pick its own actions after breaking into a machine, researchers say.

The Agentic Times · 22 Sept 2026

83

Malicious npm package posed as a Twilio bug-bounty tool

Malicious npm package posed as a Twilio bug-bounty tool

Researchers say tw-pkgprobe-7731 sat on the npm registry from mid-August 2026 and tried to harvest sensitive data from developers who installed it.

The Agentic Times · 22 Sept 2026

84

Z.ai apologises after ZCode uploaded user workspaces to the cloud

Z.ai apologises after ZCode uploaded user workspaces to the cloud

The Chinese AI firm removed the feature, commissioned two external audits and open-sourced its coding tool after developers found it shipping entire projects to Alibaba Cloud.

The Agentic Times · 22 Sept 2026

The morning agent security brief

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