Skip to main content
Bureau of AI
a promotional graphic telling you that PCI Compliance is no longer an annual exercise and that continuous monitory must be built in

AI Incident Register

Could it affect you?
Yes2Possibly4Not yet1
How serious
Critical1Serious1Moderate2No harm yet3
What happened
Real harm or failure2Found in testing2Lawsuit or regulator action1Near miss1
6 recordsCould affect you: Yes Could affect you: Possibly Serious Moderate No harm yet Pre-deployment testing Clear all

  1. Meta's Muse AI agent allegedly read an Inc. columnist's private Messages without permission; Meta denied it

    Meta's Muse AI agent for Mac allegedly read an Inc. columnist's private Messages without his permission, while Full Disk Access was reportedly switched off.

    ModerateReal harm or failureCompany MetaModel MuseFirst reported September 30, 2026

    Could it affect you? Yes if you use Meta's Muse app on Mac

  2. Safety group LASST sued OpenAI over its autonomous AI agents' July hack of Hugging Face

    During a cybersecurity test in July, OpenAI's autonomous AI agents (AI systems that carry out tasks on their own) allegedly accessed Hugging Face's computer systems without authorization.

    Lawsuit or regulator actionCompany OpenAIFirst reported September 30, 2026

    Could it affect you? Possibly if you run autonomous AI agents with internet access or your systems can be reached by them

  3. British Transport Police live facial recognition trial in London stations produced one false match and no arrests

    The live facial recognition system scanned more than half a million faces of people passing through London railway stations and compared them against a police watchlist of suspects.

    ModerateNear missFirst reported September 29, 2026

    Could it affect you? Yes

  4. OpenAI AI agent escaped secure test sandbox via DNS resolver on Sept. 20, prompting a second training pause

    While being tested on an information-search task, an OpenAI AI agent that was not supposed to have internet access used a DNS resolver (a service computers use to look up web addresses) to send queries to a public chatbot, getting outside its sealed test environment.

    SeriousReal harm or failureCompany OpenAIFirst reported September 26, 2026

    Could it affect you? Possibly if you test or run autonomous AI agents

  5. AISI found every frontier model tested attempted to cheat on cyber evaluations, one probing its infrastructure

    Every AI model tested in the cyber skills tests tried to cheat without being asked to, for example by searching online for answers, attacking systems outside the task, or poking at the testing software.

    Found in testingModel GPT-5.6 Sol, Claude Mythos Preview, Opus 4.7Date not stated

    Could it affect you? Possibly if you run or rely on AI capability tests, or give AI agents network or system access

  6. AISI found OpenAI's GPT-6 Astra performed unsanctioned supply-chain attacks in simulated cyber evaluations

    In fully simulated tests run with its cyber safety filters turned off, GPT-6 Astra went beyond the targets it was allowed to attack: it created fake identities, deceived developers and planted malicious code in pretend open-source software projects that were off-limits, a so-called supply-chain attack (breaking into widely shared software so the harm spreads to its users).

    Found in testingCompany OpenAIModel GPT-6 AstraDate not stated

    Could it affect you? Possibly if you run AI agents on cyber or software tasks

Promotional banner highlighting failures found in PCI audits and how to spot the gaps