moderate: AI 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 Clear filters

46 of 131 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
2026-10-26 reported	Anthropic's Claude agent autonomously accessed Georgia voter data hub and bypassed a paywall	Not yet classified Operational error	Anthropic	moderate	In production
2026-10-25 reported	Unauthorized third-party AI agents detected operating inside US bank customer accounts	AI acting on its own Security compromise	Meta	moderate	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
2026-10-20 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	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
2026-10-16 reported	CERT-In advisory: AI agents accessed Indian organisations' systems without authorisation	AI acting on its own Security compromise	Not stated	moderate	In evaluation
2026-10-12 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	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
2026-10-08 reported	Deepfake investment-scam ads impersonating Nigerian public figures on Facebook	AI used to exploit Other kind	Not stated	moderate	In production
2026-10-07 reported	Prompt-injected email assistant summary pushes employee toward fraudulent vendor payment	AI attacked Security compromise	Not stated	moderate	In production
2026-10-05 reported	Shinhan Bank data breach with suspected AI-assisted intrusion	AI used to exploit Security compromise	Not stated	moderate	Not stated
2026-10-04 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	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
2026-10-01 reported	Guardian test: ChatGPT and Grok remove hijab from AI-generated image of Muslim woman	AI used to exploit Harmful output	OpenAI	moderate	In production
2026-09-30 reported	AI-generated sexually explicit deepfake smear campaign against Porsche sales consultant Mu Qianwen	AI used to exploit Harmful output	Not stated	moderate	Not stated
2026-09-29 reported	Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer	Misuse by its own users Privacy leak	Meta	moderate	In production
2026-09-28 happened	Tencent Cloud agent fleet probes Alibaba Amap mapping service for over a week	AI failing in normal use Security compromise	Tencent	moderate	In evaluation
2026-09-26 reported	OpenAI agents bypass website security controls and republish SEC data	AI acting on its own Security compromise	OpenAI	moderate	Not stated
2026-09-25 reported	OpenAI agents leak 53 ChatGPT user images	AI failing in normal use Privacy leak	OpenAI	moderate	In production
2026-09-24 reported	LLM pipeline deanonymizes pseudonymous Hacker News and scientist accounts	AI used to exploit Privacy leak	Not stated	moderate	In research
2026-09-21 happened	Agentic AI-powered attack on the Dutch Institute for Vulnerability Disclosure exploited two Zammad zero-day vulnerabilities	Not yet classified Security compromise	Not stated	moderate	Not stated
2026-09-20 reported	Zhipu ZCode repository snapshot upload without clear consent	Not yet classified Privacy leak	Z.ai (Zhipu AI)	moderate	Not stated
2026-09-15 happened	AEPD-confirmed autonomous AI agent data breach (Spain)	AI acting on its own Security compromise	Not stated	moderate	Not stated
2026-08-27 reported	Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document	AI attacked Security compromise	Anthropic	moderate	In production
2026-08-10 reported	OpenClaw agent exploited a gym booking API to cancel another member's reservation while moving its user up a waitlist	AI acting on its own Agent misalignment	Anthropic	moderate	In production
2026-08-05 reported	Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account	AI attacked Security compromise	OpenAI	moderate	In production
2026-08-04 reported	AISI cyber evaluation: Mythos 5 agent bypassed an audio CAPTCHA and abused a free DNS service to point a public record at an internal target	AI acting on its own Security compromise	Anthropic	moderate	In evaluation
2026-08-04 reported	AISI cyber evaluation: concurrent Mythos 5 agents coordinated via a shared GitHub account and a leaked access token	AI acting on its own Security compromise	Anthropic	moderate	In evaluation
2026-08-04 reported	AISI cyber evaluation: Mythos 5 agent mass-created malicious GitHub repositories and its packages executed in Dependabot containers	AI acting on its own Agent misalignment	Anthropic	moderate	In evaluation
2026-08-04 reported	AISI cyber evaluation: Mythos 5 agent sent deceptive targeted emails and file transfers to real open-source maintainers	AI acting on its own Agent misalignment	Anthropic	moderate	In evaluation
2026-07-25 happened	AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues	AI acting on its own Agent misalignment	Anthropic	moderate	In evaluation
2026-07-03 happened	Wenyi AI pipeline publishes unlicensed Chinese translation of Murakami novel hours after Japanese release	AI used to exploit IP infringement	DeepSeek	moderate	In research
2026-06-09 reported	AI voice-clone grandparent scam in Florida ("crying daughter" call, $15,000 cash pickup)	AI used to exploit Other kind	Not stated	moderate	Not stated
2026-06-09 reported	Varonis phishing simulation drove an OpenClaw email agent to forward credentials and a customer export to an external address	Supply chain attack Security compromise	Google	moderate	In evaluation
2026-05-11 happened	OpenAI-attributed agents used the dormant German DseWiki as a public message board to share task answers and sandbox bypasses	AI acting on its own Agent misalignment	OpenAI	moderate	In evaluation
2026-05-05 happened	Agent swarm attributed to OpenAI published thousands of RubyGems packages, gained RCE on RubyDoc.info, and attempted API-key theft	AI acting on its own Security compromise	OpenAI	moderate	In training
2026-05-01 happened	OpenAI agents scrape and edit Wikipedia without authorization	AI acting on its own Security compromise	OpenAI	moderate	Not stated
2026-05-01 happened	Google Gemini accessed systems of three real companies during a misconfigured third-party cybersecurity evaluation	Misuse by its own users Security compromise	Google	moderate	In evaluation
2026-04-25 happened	Bee Cheng Hiang mass marketing e-mail exposes 95,000 customer addresses after AI-generated code omitted recipient hiding	Misuse by its own users Privacy leak	Not stated	moderate	In production

Browse incidents by

Risk grouping: AI acting on its own · AI used to exploit · Not yet classified · AI attacked · AI failing in normal use · Misuse by its own users · Harm by design · Supply chain attack

Kind of failure: Security compromise · Agent misalignment · Harmful output · Operational error · Privacy leak · Other kind · Hallucination · IP infringement · Physical safety

Developer: OpenAI · Anthropic · Google · Meta · Alibaba · Amazon · Character.AI · DeepSeek · Tesla · Waymo · xAI · Amazon Web Services · Character Technologies, Inc. · Replit · Salesforce · Tencent · TypeSafe AI · Univerads Technology Limited · Z.ai (Zhipu AI)

Sector: Information · Finance and Insurance · Retail Trade · Software Publishers · Public administration · technology · Transportation and Warehousing · AI platform / intermediary services · AI safety research · Artificial intelligence research and development · Arts, Entertainment, and Recreation · Autonomous vehicle / robotaxi transportation · Cloud computing · critical infrastructure and e-commerce · CRM software · Cybersecurity · education · Educational Services · Fitness and recreational sports centers · Food Manufacturing · Government AI safety and security evaluation · government AI safety evaluation · Healthcare and government · Information Security research · Insurance · Open knowledge platform / nonprofit encyclopedia · political campaigns · Public administration and government · Retail · Retail Trade; Transportation and Warehousing; Finance and Insurance · Scientific research and light source user facility · Software / AI coding tools · Software publishing / npm ecosystem

Severity: moderate · major · minor · negligible · severe

Where it happened: In production · In evaluation · In training · In research