AI Incident Registry

Public AI-incident reports, classified. 100 shown.

Attackers Manipulate AI Chatbots in Mass Disinformation, Phishing Campaign
data_poisoning high chatbot 2026-09-23
Malicious AI agents steal 600K credit cards, infect 100+ sites with skimmers
misuse critical agent 2026-09-23
This Windows Malware is Built to Let Up to Four AI Models Vote on Its Next Move
misuse medium decision_system 2026-09-23
The AI Hype Index: AI loves cheating
misuse high agent 2026-09-23
Windows CLOSEDQUORUM malware uses AI models to autonomously select post-compromise actions
misuse critical agent 2026-09-22
New ClosedQuorum Windows malware uses AI for attack decisions
misuse critical agent 2026-09-22
One Hidden Meta Muse Setting Could Let Attackers Turn the AI Assistant Into a Backdoor
safety_bypass high copilot 2026-09-22
Critical Bifrost AI Gateway Flaw Lets Attackers Run Commands Without Credentials
supply_chain critical other 2026-09-22
Microsoft Takes Down EvilTokens Device-Code Phishing Service Tied to 12,000 Inbox Compromises
misuse high other 2026-09-22
Don’t be fooled by this summer of AI hype
data_breach high other 2026-09-22
Jev introduces a new shape of LLM - System One, aka Decision Models
other low decision_system 2026-09-21
Quoting @therealcornpop
misuse low generative_media 2026-09-22
llm 0.36
other low other 2026-09-22
Microsoft disrupts AI-assisted platform that compromised 12,000 accounts
misuse high other 2026-09-22
Treasury chief says AI bosses, not their bots, will carry the can for criminal acts
governance_gap high agent 2026-09-21
Meta Muse AI app flaw lets local malware redirect dictation traffic
safety_bypass high speech 2026-09-21
Anthropic-linked CVEs pile up, attackers mostly shrug
supply_chain medium other 2026-09-21
⚡ Weekly Recap: Cisco 0-Day, AI Agent RCE, ClickFix Attacks, ClickFix Surge, and Browser Hijacks
supply_chain high agent 2026-09-21
Google confirms Gemini models hacked three companies in May 2026
supply_chain high agent 2026-09-21
Muse, Meta's extraordinarily privileged AI assistant, has a serious 0-day
safety_bypass critical agent 2026-09-21
llm-keys-ui 0.1
governance_gap medium agent 2026-09-20
Quoting voxium
governance_gap high copilot 2026-09-20
BragJack attacks hijack AI browser agents through malicious extensions
prompt_injection high chatbot 2026-09-19
Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws
misuse high chatbot 2026-09-19
FBI: Fake cop and government impersonation scams cost victims $1.6B
deepfake critical generative_media 2026-09-18
Researchers used Claude to hack OpenAI employees' ChatGPT accounts
misuse high agent 2026-09-18
RatHat Android Malware Abuses ADB to Retain Shell Access After Uninstall
misuse high agent 2026-09-18
Claimed Bug Bounty Hunter Likely Used LLM to Build PhantomRaven npm Stealer
supply_chain high other 2026-09-18
Plugin4Shell Lets Repository Owners Swap Pinned Plugin Code Across Four AI Coding Agents
supply_chain high copilot 2026-09-18
Microsoft Patches CVSS 10.0 Azure AI Foundry Flaw Enabling Unauthorized Privilege Escalation
safety_bypass critical other 2026-09-18
New WordPress Click2Shell Flaw Forces Theme Installs, Can Chain to Code Execution
supply_chain high other 2026-09-18
Gemini Hacked Three Companies in First Known Breakout by Google’s AI
excessive_agency high chatbot 2026-09-18
Researchers used Claude to hack OpenAI
misuse high chatbot 2026-09-18
US government website used Chinese model the FBI called "malicious"
supply_chain high other 2026-09-18
AI hallucination of Chinese nuclear components almost led to US military attack
model_failure critical decision_system 2026-09-18
AI coding agents' 0-click RCE flaw could hand attackers keys to the kingdom
safety_bypass critical copilot 2026-09-17
What Recent AI-Powered Attacks Mean for Your Identity Security
misuse high other 2026-09-17
New RatHat Android malware uses AI to automate device control
misuse high agent 2026-09-17
CISO's Expert Guide to Agentic Pentesting for Websites
governance_gap high agent 2026-09-17
Can You Prove a New CVE Is Exploitable Before Attackers Do? Learn How in This Webinar
governance_gap high other 2026-09-17
Operation “Date Bait”: AI-enabled scam targeting loveseekers
misuse high chatbot 2026-02-01
Operation “False Witness”: Fake recovery service impersonating authorities
misuse high chatbot 2026-02-01
Romance scams: AI-enabled romance scam workflows
misuse high chatbot 2026-02-01
Self-generated prompt injections in compaction summaries
prompt_injection high agent 2026-09-17
LLMs respond differently to harmful prompts when AI watermarking is used
safety_bypass high chatbot 2026-09-17
Small AI models let drones autonomously identify and attack battlefield targets
excessive_agency critical autonomous_system 2026-09-17
Spain gets its first taste of AI-aided cyber attack
governance_gap high other 2026-09-16
BragJack Attack Can Turn a Browser's Agentic AI Against It
prompt_injection high agent 2026-09-16
Spain's data agency gets first report of AI-powered data breach
data_breach high agent 2026-09-16
Threat Intelligence Alone Won't Close the Exploitation Gap
governance_gap high other 2026-09-16
Attacker Hijacks AI Coding Assistant Session, Spreads Shai-Hulud Across About 100 Repositories
supply_chain critical copilot 2026-09-16
Black Hat USA 2026 | The 'Breaking' News: The OpenAI–Hugging Face Incident
excessive_agency critical agent 2026-09-15
What Zero-Day Response Should Be in the Post-Mythos Era
governance_gap medium other 2026-09-15
Human Attacker Exploits Marimo RCE, Reaches SSH Bastion in Eight Seconds
supply_chain high other 2026-09-15
OpenAI's malicious bot swarm attacked RubyGems
supply_chain medium agent 2026-09-14
SpiderSilk Hunts External Threats With AI-Based Scanner
other low decision_system 2026-09-11
AI Changed the Exposure Problem. Validation Needs to Change With It.
governance_gap medium other 2026-09-14
⚡ Weekly Recap: Rogue AI Agents, WeChat Worm, PaperCut Attacks, AI Espionage, and Rootkits
excessive_agency high agent 2026-09-14
Microsoft’s Patching
governance_gap high other 2026-09-14
The contagion of fear
governance_gap low other 2026-09-14
OpenAI Agents Linked to RubyGems Campaign That Gained RCE on RubyDoc Servers
supply_chain critical agent 2026-09-12
Papercut AI Swarm Attack Heralds Changes for Cyber Kill Chain
misuse high agent 2026-09-11
AI Governance Can't Wait
safety_bypass high decision_system 2026-09-11
Threat Actor Generates 1M Personalized Fraud Emails in 3 Days
misuse critical generative_media 2026-09-11
How Threat Actors Are Turning Trusted AI Platforms Into an Attack Surface
misuse high chatbot 2026-09-11
Hackers abused Claude to extract secrets from 1.8M Android apps
misuse high chatbot 2026-09-11
Russian State-Sponsored Hackers Use Claude to Rebuild Malware After Detection
misuse high chatbot 2026-09-11
Claude Used to Automate Exploitation and Data Theft Across Multiple Victims
misuse critical chatbot 2026-09-11
Quoting huggingface.co/security.txt
governance_gap low other 2026-09-11
OpenAI agents attacked RubyGems back in May
excessive_agency high agent 2026-09-12
Hundreds of AI agents helped PaperCut attacker hit 395+ orgs, and some went off script
excessive_agency critical agent 2026-09-10
AI-powered attack exploited PaperCut flaws to hack 395 organizations
misuse critical agent 2026-09-10
Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6
excessive_agency high agent 2026-09-10
PaperCut Attacker Uses Hundreds of AI Agents to Compromise 440+ Instances
misuse critical agent 2026-09-10
AIs Compress Exploit Timeline
safety_bypass high agent 2026-09-10
4 groups caught using the same Chrome and Windows exploit kit
supply_chain high other 2026-09-09
WeChat worm could pwn a friend before they even answered the call
safety_bypass high other 2026-09-09
Identity-Based AI Attack Threatens Security of Enterprise Data
safety_bypass high agent 2026-09-09
US Government Accuses Chinese AI Firms of Distilling Frontier Models
data_breach high other 2026-09-09
US says Chinese firms extracted billions of tokens from frontier AI models
supply_chain high other 2026-09-09
U.S. Agencies Accuse China AI Firms of Distilling Claude, GPT, Gemini, and Grok
supply_chain high other 2026-09-09
DeepSeek Harness Flaw Let AI Agents Disable Their Own File Sandbox Without Approval
safety_bypass high agent 2026-09-09
Webinar: Learn How to Answer “Are We Exposed?” Faster After a New CVE
governance_gap medium other 2026-09-09
Infostealer Logs Expose Replayable AI Tokens That Can Bypass MFA
data_breach high other 2026-09-09
Election information and safeguards in 2026
governance_gap low other 2026-05-27
Quoting Calif Research
safety_bypass high other 2026-09-10
OpenAI's Artifactory opened covert data-stealing channel alongside Hugging Face attack
supply_chain critical other 2026-09-08
OpenAI Agents Took Over Wiki Site Before Hugging Face Attack
excessive_agency medium agent 2026-09-08
Hackers build AI frameworks for widescale credential theft
misuse high agent 2026-09-08
Autonomous AI Agents Compromise Thousands of Credentials in Under Six Hours
misuse critical agent 2026-09-08
ChatGPT Flaw Let a Planted Prompt Send a Victim's Gmail Data to Another Account
prompt_injection high chatbot 2026-09-08
Microsoft Plugs Nearly 1,000 Security Holes
governance_gap medium other 2026-09-08
Stealing AI Reasoning Traces
safety_bypass critical chatbot 2026-09-08
AIs as Modern Genies
excessive_agency high agent 2026-09-08
On the Navier–Stokes Millennium Prize Problem
governance_gap medium other 2026-09-08
llm 0.34
other low other 2026-09-02
OpenAI admits it didn't disclose rogue AI wiki hijacking incident
governance_gap high agent 2026-09-05
AI Is Ending the Era of Hidden Vulnerabilities — Are Vendors Ready?
governance_gap medium other 2026-09-04
GPT-6 Astra Scores 100% on ExploitBench as OpenAI Blocks PoC Exploit Requests
governance_gap high chatbot 2026-09-04
Phishing Campaign Sends Millions of Emails Using Invisible Unicode to Evade Filters
prompt_injection high other 2026-09-04