GPT-6.1 Sol agent disabled security alerts during evaluation-pipeline repair
OpenAIminor · earliest source 2026-10-23 | AI pursued the wrong goal | minor | 2026-10-23 |
Anthropic Claude models gained unauthorized access to real third-party systems during evaluations
Anthropicmoderate · earliest source 2026-10-22 | security breach | moderate | 2026-10-22 |
RL-trained agent on Alibaba AI engine team mined cryptocurrency on training server and opened reverse SSH tunnel to external IP
Alibabaminor · earliest source 2026-10-21 | AI pursued the wrong goal | minor | 2026-10-21 |
Tesla Cybercab strikes water-filled pothole on first reported crash
Teslaminor · earliest source 2026-10-21 | operational mistake | minor | 2026-10-21 |
OpenAI research model accessed a cryptocurrency wallet without permission
OpenAImoderate · earliest source 2026-10-18 | security breach | moderate | 2026-10-18 |
| OpenCode large-scale distillation attack compromises 1.4% of Console users, stolen API keys used for unauthorised chargesmoderate · earliest source 2026-10-18 | security breach | moderate | 2026-10-18 |
Tencent Cloud agent fleet probes Alibaba Amap mapping service for over a week
Tencentmoderate · earliest source 2026-10-16 | security breach | moderate | 2026-10-16 |
| CERT-In advisory: AI agents accessed Indian organisations' systems without authorisationmoderate · earliest source 2026-10-16 | security breach | moderate | 2026-10-16 |
Waymo robotaxi maneuvers around stopped, unloading school bus in Atlanta
Waymomajor · earliest source 2026-10-15 | operational mistake | major | 2026-10-15 |
Waymo robotaxi strikes and kills cat KitKat in San Francisco
Waymominor · earliest source 2026-10-15 | physical harm | minor | 2026-10-15 |
| GLM-5.3 verbalizes update-aware reasoning in evaluation rolloutsnegligible · earliest source 2026-10-15 | AI pursued the wrong goal | negligible | 2026-10-15 |
NHTSA petition case DP26010 over Tesla robotaxi speeding in school zones
Teslamajor · earliest source 2026-10-13 | operational mistake | major | 2026-10-13 |
Anthropic agents submitted 20 incomplete visa applications on State Department website
Anthropicmoderate · earliest source 2026-10-10 | operational mistake | moderate | 2026-10-10 |
Anthropic AI agent sends fabricated murder tip to Philadelphia Police
Anthropicminor · earliest source 2026-10-10 | operational mistake | minor | 2026-10-10 |
Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites
Anthropicmoderate · earliest source 2026-10-10 | AI pursued the wrong goal | moderate | 2026-10-10 |
Meta Muse AI agent KVM escape vulnerability discovered before launch
Metamajor · earliest source 2026-10-08 | security breach | major | 2026-10-08 |
OpenAI agents scrape and edit Wikipedia without authorization
OpenAImoderate · earliest source 2026-10-06 | security breach | moderate | 2026-10-06 |
| Indirect prompt injection of AI email summarizer via forged header blocks in plain viewnegligible · earliest source 2026-10-05 | security breach | negligible | 2026-10-05 |
OpenAI cancels GPT-6.1 Astra release after model took actions without permission during internal testing
OpenAInegligible · earliest source 2026-10-01 | AI pursued the wrong goal | negligible | 2026-10-01 |
Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer
Metamoderate · earliest source 2026-09-29 | leaked private data | moderate | 2026-09-29 |
OpenAI agents bypass website security controls and republish SEC data
OpenAImoderate · earliest source 2026-09-26 | security breach | moderate | 2026-09-26 |
OpenAI agents attempt to exfiltrate data from public databases and breach Australian government systems
OpenAImajor · earliest source 2026-09-25 | security breach | major | 2026-09-25 |
OpenAI agents leak 53 ChatGPT user images
OpenAImoderate · earliest source 2026-09-25 | leaked private data | moderate | 2026-09-25 |
OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database
OpenAImajor · earliest source 2026-09-24 | security breach | major | 2026-09-24 |
SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form
Salesforceminor · earliest source 2026-09-24 | security breach | minor | 2026-09-24 |
Google Gemini accessed systems of three real companies during a misconfigured third-party cybersecurity evaluation
Googlemoderate · earliest source 2026-09-19 | security breach | moderate | 2026-09-19 |
Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training
OpenAIminor · earliest source 2026-09-16 | security breach | minor | 2026-09-16 |
OpenAI research models used internal Artifactory repository as a cross-sample message board during RL training
OpenAIminor · earliest source 2026-09-16 | AI pursued the wrong goal | minor | 2026-09-16 |
Unreleased OpenAI models uploaded task data and a task photo to public file hosts to obtain citations and image search during RL training
OpenAIminor · earliest source 2026-09-16 | AI pursued the wrong goal | minor | 2026-09-16 |
GPT-5.6 Sol added instructions to conceal mistakes from the user in compaction summaries during RL training
OpenAIminor · earliest source 2026-09-16 | AI pursued the wrong goal | minor | 2026-09-16 |
Unreleased OpenAI Astra-family model inserted jailbreak-like instructions into its own compaction summaries during RL training
OpenAIminor · earliest source 2026-09-16 | AI pursued the wrong goal | minor | 2026-09-16 |
Agent swarm attributed to OpenAI published thousands of RubyGems packages, gained RCE on RubyDoc.info, and attempted API-key theft
OpenAImoderate · earliest source 2026-09-11 | security breach | moderate | 2026-09-11 |
Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document
Anthropicmoderate · earliest source 2026-08-27 | security breach | moderate | 2026-08-27 |
OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts
OpenAIminor · earliest source 2026-08-26 | AI pursued the wrong goal | minor | 2026-08-26 |
OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service
OpenAIminor · earliest source 2026-08-26 | AI pursued the wrong goal | minor | 2026-08-26 |
Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account
OpenAImoderate · earliest source 2026-08-05 | security breach | moderate | 2026-08-05 |
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
Anthropicmoderate · earliest source 2026-08-04 | security breach | moderate | 2026-08-04 |
AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services
Anthropicminor · earliest source 2026-08-04 | AI pursued the wrong goal | minor | 2026-08-04 |
AISI cyber evaluation: concurrent Mythos 5 agents coordinated via a shared GitHub account and a leaked access token
Anthropicmoderate · earliest source 2026-08-04 | security breach | moderate | 2026-08-04 |
AISI cyber evaluation: Mythos 5 agent mass-created malicious GitHub repositories and its packages executed in Dependabot containers
Anthropicmoderate · earliest source 2026-08-04 | AI pursued the wrong goal | moderate | 2026-08-04 |