Incidents

What has gone wrong with AI systems, where, and how badly.

Risk grouping Kind of failure The AI's part Developer Sector Severity Where it happened

124 of 124 incidents

Risk groupings are set by a model from sentences quoted from each incident's sources. On 2026-10-24 a second model (deepseek-reasoner) classified 55 incidents without seeing those answers: it chose the same grouping for 36; for 10 one of the two left a question unanswered; 9 differ.

Date	Incident	Risk grouping	Developer	Severity	Where it happened
2026-10-23 reported	Garage-built ChatGPT-controlled smart rifle fires on voice command; OpenAI revokes engineer's access	AI used to exploit Physical safety	Not stated	minor	Not stated
2026-10-23 reported	302.ai public Azure bucket exposed 17.6 million files including 144,000 AI chat logs	Not yet classified Privacy leak	Univerads Technology Limited	major	In production
2026-10-23 reported	BUGSTER uses DeepSeek-powered Hermes Agent to breach university MongoDB, stealing 5,200+ records	AI used to exploit Security compromise	DeepSeek	moderate	In production
2026-10-22 reported	Anthropic Claude models gained unauthorized access to real third-party systems during evaluations	AI acting on its own Security compromise	Anthropic	moderate	In evaluation
2026-10-21 reported	RL-trained agent on Alibaba AI engine team mined cryptocurrency on training server and opened reverse SSH tunnel to external IP	AI acting on its own Agent misalignment	Alibaba	minor	In training
2026-10-21 reported	Tesla Cybercab strikes water-filled pothole on first reported crash	Not yet classified Operational error	Tesla	minor	In production
2026-10-21 reported	ARTEX autonomous penetration-testing agent used in attacks on South Korean financial institutions	AI used to exploit Security compromise	Not stated	major	Not stated
2026-10-20 reported	China-linked autonomous AI agent Artex used in cyberattacks on Japanese and South Korean firms	AI used to exploit Security compromise	Not stated	major	Not stated
2026-10-20 reported	AI-generated 'Xiaohai' teen persona used to sell products to older women via fabricated sob stories	AI used to exploit Harmful output	Not stated	moderate	In production
2026-10-19 reported	ICMP evidence that Google Gemini reproduced lyrics by Australian artists	Misuse by its own users IP infringement	Google	moderate	Not stated
2026-10-18 reported	Deepfake video of President Marcos used to defraud Tarlac dentist of P93 million	Not yet classified Other kind	Not stated	major	Not stated
2026-10-18 reported	OpenAI research model accessed a cryptocurrency wallet without permission	AI acting on its own Security compromise	OpenAI	moderate	In research
2026-10-18 reported	OpenCode large-scale distillation attack compromises 1.4% of Console users, stolen API keys used for unauthorised charges	AI attacked Security compromise	Not stated	moderate	Not stated
2026-10-18 reported	Nude deepfakes of Austrian MEP Lena Schilling and 49 other MEPs circulated online	AI used to exploit Harmful output	Not stated	major	Not stated
2026-10-17 reported	Character.AI chatbots promoted as therapists/psychologists; states cite 2024 wrongful-death suit and privacy concerns in bankruptcy filing	Harm by design Harmful output	Character Technologies, Inc.	major	In production
2026-10-16 reported	Indirect prompt injection attempts embedded in HTTP response headers across websites	AI attacked Security compromise	Not stated	minor	Not stated
2026-10-16 reported	CERT-In advisory: AI agents accessed Indian organisations' systems without authorisation	AI acting on its own Security compromise	Not stated	moderate	In evaluation
2026-10-16 reported	Eight state attorneys general sue OpenAI over alleged harms to teenage ChatGPT users	Harm by design Harmful output	OpenAI	major	Not stated
2026-10-16 reported	Backdoored open-weight model exfiltrates project credentials through OpenAI Codex CLI	Harm by design Security compromise	Not stated	minor	In evaluation
2026-10-15 happened	Storm-0940 uses ARTEX agentic AI framework to automate cross-tenant password spraying and OAuth application abuse, including ConnectWise…	AI used to exploit Security compromise	Not stated	major	In production
2026-10-15 reported	HiddenLayer indirect prompt injection against TypeSafe AI Jev decision model browser agent	Supply chain attack Security compromise	TypeSafe AI	negligible	In evaluation
2026-10-15 reported	Waymo robotaxi maneuvers around stopped, unloading school bus in Atlanta	Not yet classified Operational error	Waymo	major	In production
2026-10-15 reported	GLM-5.3 verbalizes update-aware reasoning in evaluation rollouts	Not yet classified Agent misalignment	Not stated	negligible	In evaluation
2026-10-13 reported	NHTSA petition case DP26010 over Tesla robotaxi speeding in school zones	Not yet classified Operational error	Tesla	major	In production
2026-10-12 reported	AI deepfake ads depicting Wisconsin congressional candidate Rebecca Cooke	Not yet classified Harmful output	xAI	minor	Not stated
2026-10-12 reported	CyberXero AI-augmented initial access campaign using Claude Code and PentAGI agents	AI used to exploit Security compromise	Anthropic	major	Not stated
2026-10-12 reported	Fideuram (Intesa Sanpaolo private banking) deepfake voice/video executive impersonation fraud	AI used to exploit Other kind	Not stated	major	In production
2026-10-12 reported	Anthropic Mythos-discovered Rejetto HFS authentication bypass exploited in the wild	Misuse by its own users Security compromise	Anthropic	moderate	In research
2026-10-11 reported	AI-morphed obscene image used to blackmail 19-year-old in Mangaluru	AI used to exploit Other kind	Not stated	moderate	Not stated
2026-10-10 reported	Anthropic agents submitted 20 incomplete visa applications on State Department website	Not yet classified Operational error	Anthropic	moderate	Not stated
2026-10-10 reported	AgentCorruption: prompt-injected Bedrock AgentCore agent exfiltrates execution-role credentials via IMDS	AI attacked Security compromise	Amazon	major	In production
2026-10-10 reported	AI-assisted LinkedIn scraping used to build 'Traitorbase' doxxing spreadsheet targeting RNLI staff and anti-racism activists	AI used to exploit Privacy leak	Not stated	moderate	Not stated
2026-10-10 reported	Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites	AI acting on its own Agent misalignment	Anthropic	moderate	In evaluation
2026-10-09 reported	US intelligence chatbot fabricated Chinese nuclear vessel intelligence	AI failing in normal use Hallucination	Not stated	major	Not stated
2026-10-09 reported	Kentucky Attorney General lawsuit against Character.AI over chatbots advising self-harm and suicide	AI failing in normal use Harmful output	Character.AI	major	Not stated
2026-10-08 reported	Deepfake investment-scam ads impersonating Nigerian public figures on Facebook	AI used to exploit Other kind	Not stated	moderate	In production
2026-10-08 reported	DB-GPT 0.8.0 unauthenticated RCE via sandbox fallback and skill_upload directory traversal (CVE-2026-51862, CVE-2026-51869)	AI used to exploit Security compromise	Not stated	major	In production
2026-10-08 reported	Meta Muse AI agent KVM escape vulnerability discovered before launch	Not yet classified Security compromise	Meta	major	Not stated
2026-10-07 reported	Agentjacking demonstration against Fortune 100 company hijacks over 100 agents via injectable Sentry DSNs	AI attacked Security compromise	Not stated	major	Not stated
2026-10-07 reported	Prompt-injected email assistant summary pushes employee toward fraudulent vendor payment	AI attacked Security compromise	Not stated	moderate	In production
2026-10-07 reported	Autonomous AI agent framework (Strix/Cairn/Hermes) used to attack hundreds of online retailers and steal card data	AI used to exploit Security compromise	Not stated	major	Not stated
2026-10-05 reported	Shinhan Bank data breach with suspected AI-assisted intrusion	AI used to exploit Security compromise	Not stated	moderate	Not stated
2026-10-05 reported	Claude Code agent deletes 48,218 Windows project files and damages Git object store	Misuse by its own users Operational error	Anthropic	minor	Not stated
2026-10-05 reported	Indirect prompt injection of AI email summarizer via forged header blocks in plain view	AI attacked Security compromise	Not stated	negligible	In evaluation
2026-10-05 reported	Airline chatbot fabricated bereavement refund policy	AI failing in normal use Hallucination	Not stated	minor	Not stated
2026-10-04 reported	Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposure	AI attacked Security compromise	Not stated	moderate	In production
2026-10-04 reported	AI agent breach of KB Kookmin Bank mobile work support system	AI acting on its own Security compromise	Not stated	major	Not stated
2026-10-04 reported	OpenClaw agent deletes hundreds of emails from primary Gmail account	AI failing in normal use Operational error	Not stated	minor	In production
2026-10-04 reported	OpenAI agents scan UNCTAD site over 16,000 times and escalate bypass techniques	AI acting on its own Security compromise	OpenAI	moderate	Not stated
2026-10-03 reported	Microsoft reports 50 prompt-based attempts to poison AI assistant memory across 31 companies	AI attacked Security compromise	Not stated	moderate	Not stated

Page 1 of 3 · Next