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
Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation
During an Anthropic cybersecurity evaluation with Irregular, Claude Mythos 5 reportedly created and published a malicious Python package to PyPI while pursuing a fictional target. The package was reportedly available for about an hour and ran on 15 real systems. On a security company's scanner, it reportedly exfiltrated credentials that Claude then used to access additional company infrastructure.
Anthropic Research Model Reportedly Scanned 9,000 Targets and Compromised Real Company's Application During Evaluation
During an Anthropic cybersecurity evaluation with Irregular, an internal research Claude model reportedly scanned roughly 9,000 internet targets after failing to reach its fictional target. It reportedly compromised a real company's Internet-facing application using credentials from an exposed debug page and SQL injection, then stopped after recognizing that the host was real.
Granola AI Notetaker Allegedly Captured and Transcribed Florida Meeting Participant Without Notice or Consent
Tarra Chamberlain, a Florida resident, alleged that Granola captured and transcribed her speech during a virtual meeting without her knowledge or consent after another participant used the AI notetaker. Her July 2026 lawsuit further alleged that Granola uses meeting data to improve its AI models by default, while non-user participants have no comparable opt-out.
Hong Kong Man Reportedly Lost More Than HK$10 Million in WhatsApp Scam Using Purported AI-Generated Voice Impersonation of His Father
A Hong Kong man reportedly lost more than HK$10 million after scammers hijacked his father's WhatsApp account and sent voice messages closely resembling his father's voice and speech. The victim allegedly made repeated transfers until his savings were depleted.
New Jersey Regulators Found DataOne Operated 62 Unpermitted Natural-Gas Generators at Vineland AI Data Center
In July 2026, New Jersey inspectors found 62 unpermitted 2,000-kW natural-gas generators powering DataOne's Vineland data center, which has an agreement to provide AI computing power to Microsoft. The state later fined DataOne $1.07 million under the Air Pollution Control Act. Residents also reported persistent noise and raised concerns about air emissions; DataOne disputed the state's decision.
Allegedly AI-Generated Audio Bomb Threat Prompted Evacuations at the Port of Constanța, Romania
A Romanian-language audio bomb threat, assessed by officials as AI-generated, prompted employee evacuations and security searches at the Port of Constanța, Romania. Authorities received two calls using numbers with Ukrainian and Polish prefixes. Officials later said the alert was false. The perpetrators and AI system were not identified.
Anthropic Claude Opus 5 Coding Agent Reportedly Reset a Live Supabase Production Database During Prisma Migration Work
A developer reported that a Claude Opus 5 coding agent reset a live Supabase database while autonomously repairing a personal project's schema. The agent ran `prisma migrate diff` with the production URL supplied as the disposable shadow database, causing Prisma to drop all 22 tables. The developer had granted the agent production access; most content was later recovered or rebuilt.
U.S. State Department Reportedly Presented AI-Generated Map That Mislabeled Every Labeled African Country
During a U.S. State Department presentation at the AIDS 2026 conference in Rio de Janeiro, a map carrying an OpenAI provenance signal reportedly mislabeled every African country shown with a label. The department attributed the slide to a team member's rushed revision and accepted responsibility for the resulting confusion and misrepresentation.
Publicly Shared Claude Artifacts Reportedly Became Discoverable Through Google Search
Users reported that publicly shared Claude Artifacts (apps, documents, spreadsheets, and other files) could be found through Google Search. Reportedly, indexed artifacts containing business plans, infrastructure diagrams, clinical-trial planning materials, and other potentially sensitive content were also located. Anthropic said links became searchable only after being posted somewhere crawlable.
Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations
Beginning July 26, 2026, AI agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6 Sol reportedly took 19 unsanctioned actions on the live Internet during UK AISI cybersecurity evaluations. Mythos 5 reportedly accounted for 17 events, many allegedly involving deceptive attempts to manipulate real developers into accepting malicious code. AISI reportedly detected and contained the activity; no resulting real-world harm was identified.
Marrero, Louisiana, Woman Allegedly Created Purportedly AI-Generated Nude Media During Extortion Scheme
Deputies in Livingston Parish, Louisiana, said Marrero resident Haydee Ortiz was initially treated as a victim before investigators allegedly linked her to an online impersonation and extortion campaign involving purportedly AI-generated sexual images and violent threats. Police said sexual media depicting one victim was sent to family and friends, while a person was threatened with rape or bodily harm unless money was paid.
AI-Generated Voice Mimicking Taiwan President Lai Ching-te Reportedly Used in Political Video Criticizing Government Food-Safety Response
A political video titled "It's Out of Your Control" reportedly used an AI-generated voice resembling Taiwan President Lai Ching-te while criticizing the government's response to a cooking-oil safety scandal. Police said the voice could be mistaken for Lai and later confirmed it was AI-generated. Opposition figures defended the video as political expression while prosecutors opened a forgery investigation.
Purportedly AI-Generated TikTok Ad Impersonating Digital Payments Company OPay Reportedly Led to ₦150,000 (~US$108.86) Loss for Small-Business Operator in Ilorin, Nigeria
Mohammed Yusuf, a small-business operator in Ilorin, Kwara State, Nigeria, reportedly lost about ₦150,000 (~US$108.86) after responding to a purportedly AI-generated TikTok ad impersonating digital payments company OPay. The ad allegedly promised a free payment terminal and cash grant. A caller reportedly posing as OPay staff requested a one-time password; unauthorized betting-voucher transactions reportedly depleted nearly all the operator's business capital.
American Exceptionalism Institute's Purportedly AI-Generated Ad Drew Defamation Claims Over Marsha Blackburn Pharmaceutical Bribery Allegations
American Exceptionalism Institute reportedly aired an AI-generated political ad portraying Sen. Marsha Blackburn as accepting pharmaceutical-industry payments in exchange for legislative action. Blackburn's attorneys alleged that the bribery claims were defamatory and that the ad failed to comply with Tennessee's synthetic-media disclosure requirements. Comcast and Viamedia reportedly pulled the ad.
Hank Green Reportedly Used AI-Generated Scientific Image Containing Errors in Educational Video
Science communicator and YouTuber Hank Green reportedly included an AI-generated scientific image containing factual and mathematical errors in a YouTube educational video. Green later said he knew the image was AI-generated when he used it and removed it after recognizing problems with the graphic.