AI Incidents
Real-world cases where AI systems caused harm, classified by risk domain and entity. Data sourced from 
AIID and classified by 
MIT AI Risk Initiative. CC BY-SA 4.0
253 incidents
Anthropic's Claude Code AI Agent Reportedly Deleted About 48,000 Live Project Files and Version-Control History During Software Repair
A Claude Code user reportedly authorized an AI coding agent to repair isolated copies of software used to analyze historical stock-options data. A sub-agent allegedly followed Windows directory junctions into the live project tree, deleting about 48,218 files and the Git object store in 103 seconds. The account has not been independently verified.
AI Chatbot Reportedly Misidentified Chinese Ship Cargo as Nuclear-Program Components, Prompting U.S. Military Interception Preparations
In spring 2026, a U.S. special operations analyst reportedly used an AI chatbot to analyze intelligence on a Chinese ship's cargo and produced a report falsely identifying it as carrying nuclear-weapons-program components. The U.S. military reportedly prepared to intercept and potentially board the vessel, with aircraft already airborne, before officials rechecked the report, found the AI-assisted conclusion was wrong, and called off the operation.
Z.ai's ZCode AI Coding Assistant Reportedly Uploaded Developers' Local Code Repositories to Alibaba Cloud Without Consent
Developers reported that Z.ai's ZCode AI coding assistant uploaded local code repositories to Alibaba Cloud without consent. Z.ai said a default-enabled Codebase Indexing feature caused the behavior, apologized, patched the vulnerability, and later disabled the upload path. One company retracted a separate claim that six workspaces containing sensitive data had been uploaded; Z.ai said independent reviews found no code data retained.
Fraud Ring in Greece Allegedly Used AI-Cloned Relatives' Voices to Steal Money and Valuables
Greek police alleged that a fraud ring used AI-cloned voices of victims' relatives to validate calls impersonating utility and telecom workers, persuading victims to surrender money and valuables. Police arrested two alleged collectors in Nea Ionia, Attica, after a theft of valuables worth €30,000, and estimated the organization's total illicit proceeds at over €1 million.
AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority
An unnamed organization reportedly notified Spain's data protection authority that a third party used an AI agent powered by a known language model to carry out a multistep intrusion that resulted in unauthorized changes to personal data and access to invoices. The AEPD said the case remains under review and has not identified the organization, attacker, AI system, attack date, or number of affected people.
AI-Generated Images Purporting to Show Donald Trump Kissing White House Aide Natalie Harp Went Viral on Social Media
AI-generated images purporting to show U.S. President Donald Trump kissing White House aide Natalie Harp on a golf course spread across social media; one X post received over 10 million views. Forensic analysis and provenance checks indicated the circulating images were synthetic, and the White House called them fake. The original creator remained unidentified.
Anthropic-Designated GTG-87001 Weapons Cell in Northern Yemen Reportedly Used Claude Code to Develop Missile Guidance Software
Anthropic reported that a northern Yemen-based weapons cell, designated GTG-87001, used Claude Code across three weapons programs to develop guidance, navigation, and control software. The actors reportedly test-fired a guided rocket that appeared to fail, then returned to Claude for failure analysis. Anthropic said it banned associated accounts and shared threat intelligence with partners.
Russia-Linked Matryoshka Influence Operation Reportedly Used AI-Cloned Celebrity Voices and Fabricated News-Style Videos to Target Democratic Candidates Ahead of 2026 U.S. Midterms
Researchers attributed a September 2026 influence campaign targeting U.S. Democratic Senate candidates to the Russia-linked Matryoshka/Operation Overload network. The campaign reportedly used AI-cloned celebrity voices and fabricated, news-branded videos to spread false or unsubstantiated claims on social media. Celebrities and CNN rejected the manipulated statements and unauthorized branding, which were intended to influence U.S. voters before the midterms.
India-Based Sextortion Gang Allegedly Used AI-Generated Sexual Videos to Extort Canada-Based Indian Victim
Police in Ghaziabad, India, alleged that four members of a sextortion gang recorded a Canada-based Indian victim during a Facebook Messenger video call, created sexually explicit AI videos depicting the victim, and demanded $50,000 while threatening to circulate the material. Police said the victim reported the demand and that AI sextortion videos were found on the suspects' phones.
Delhi Man Allegedly Used AI to Create and Circulate Obscene Images of College Acquaintance
Delhi police alleged that a man named Keshav Bansal used photographs from a college acquaintance's private social media account with AI image-generation and editing tools to create obscene morphed images and upload them to anonymous Discord servers. The woman reported fake accounts and threatening messages intended to humiliate and harass her. Police arrested Bansal and said the investigation was ongoing.
Early Claude Opus 4.6 Checkpoint Reportedly Gained Unauthorized Admin Access to Third-Party System During Cybersecurity Evaluation
Anthropic reported that during a January 2026 cybersecurity evaluation, an early checkpoint of Claude Opus 4.6 accidentally disabled its assigned target, then reached an unrelated third-party machine over the open Internet. The model reportedly used a discovered password for admin access, harvested additional credentials, changed system settings, and read one person's personal information before its token budget ended. Anthropic later notified the affected party.
Purported Deepfake WhatsApp Scam Impersonating Tamil Nadu Chief Minister and Actor C. Joseph Vijay Reportedly Defrauded Bengaluru Security Guard of ₹104,000 (~$1,085.40)
Ratikanta Giri, a 29-year-old security guard in Bengaluru, India, reportedly lost ₹104,000 (~$1,085.40) after a WhatsApp video caller used a purportedly AI-generated deepfake to impersonate C. Joseph Vijay, the actor and chief minister of the southern Indian state of Tamil Nadu. The caller promised financial aid, while accomplices allegedly demanded fees and later impersonated India's Central Bureau of Investigation.
Northern Ireland Victim Reportedly Lost £250,000 in Investment Scam Using Purportedly AI-Generated Video of Unnamed Financial Personality
A person in Ards and North Down, Northern Ireland, reportedly lost £250,000 in an investment scam that began with an apparently AI-generated video of an unnamed, well-known financial personality. Police said the victim was moved to WhatsApp, persuaded to make escalating payments, create online accounts, grant remote computer access, and borrow money to keep investing.
Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns
During the 2026–27 school year, Parkview High School in Lilburn, Georgia, reportedly received at least four AI-generated bomb threats, including masked phone calls that prompted repeated lockdowns or soft lockdowns. School police described the threats as following a recurring pattern and were investigating with the GBI and FBI. Authorities had not identified a suspect or established publicly whether the same person was responsible for every threat.
Instinct AI Personal Assistant Reportedly Sent Email From Moxxie Ventures Founder's Account Without Approval
Moxxie Ventures founder Katie Jacobs Stanton reported that Instinct, a private-access AI personal assistant, sent an innocuous email from her connected account without checking with her first. Stanton said the unauthorized action broke her trust and led her to disconnect email access. Instinct's operator, Spear Street Technology, later said it was taking early users' security concerns seriously and had made changes to prevent some actions.