| 2026-11-16 | OpenAI ExploitGym post-mortem: Astra research agents escalate privileges in CI and conceal access | Agent escapes its sandbox | OpenAI | Flaw fixed, Policy changed, Product or feature pulled | BigGo Finance |
| 2026-11-15 | JPCERT/CC-led probe finds around 1,000 servers likely used for AI-driven cyberattacks | AI used to run a cyber attack | | New monitoring put in place | The Straits Times |
| 2026-11-14 | ARTEX agentic penetration framework used in Chinese-nexus intrusion campaigns (Amazon MadPot observations) | Harmful content and jailbreaks | ARTEX | | Cyber Security News |
| 2026-11-14 | Threat actors weaponize ARTEX autonomous penetration-testing agents for intrusions and data exfiltration | AI used to run a cyber attack | ARTEX | Product or feature pulled | CASRAI |
| 2026-11-14 | Account drain and hack of Opus 4.6's Manifold mana account (AI Village) | | AI Village | Publicly disclosed | LessWrong |
| 2026-11-13 | Pliny breach of Claude Code exposes full system prompts and tool definitions | Deception, concealment or sabotage | Claude Code | | 36Kr |
| 2026-11-13 | Trajectory agents attempt exploits and impersonation against Epoch website during impossible-task eval (2026-10-20) | Gaming the task (reward hacking) | | Product or feature pulled | Epoch AI |
| 2026-11-13 | Tesla Cybercab robotaxi allegedly ran a red light and braked for phantom obstacles in Texas (Clarkson column) | Physical harm | | Lawsuit or legal claim filed | UA.NEWS |
| 2026-11-13 | Podqi investigation: ChatGPT, Gemini and Perplexity shopping answers included risky sites | Harmful content and jailbreaks | | | 디지털투데이 |
| 2026-11-12 | CL-STA-1238 autonomous intrusion campaign using the Cairn framework (August–September 2026) | Harmful content and jailbreaks | Cairn | | Bold News |
| 2026-11-11 | ARTEX-driven autonomous intrusion campaign against cloud environments (Unit 42 observations) | AI system attacked or breached | ARTEX | Product or feature pulled | Unit 42 |
| 2026-11-11 | Paul Hebert's ChatGPT spiral, reported by Fort Worth Weekly | Made-up output relied on | OpenAI | Lawsuit or legal claim filed, Policy changed | Fort Worth Weekly |
| 2026-11-11 | AntiFox agentic framework intrusions against AWS credentials (as reported via GitGuardian blog) | Credential and privilege abuse | AntiFox | | BleepingComputer |
| 2026-11-11 | Hacking group used Hermes AI agent to steal over 2,000 sensitive files from Tajik government document system | Data leaked or sent out | Hermes | | Drop Site News |
| 2026-11-11 | Bombay High Court quashes customs Order-in-Original citing non-existent Supreme Court judgments (Quanta Logistics) | Made-up output relied on | | Access removed | MediaNama |
| 2026-11-10 | Meta Muse AI agent laptop purchase: card payment from cloud VM flagged, order cancelled by merchant, repurchased manually | Agent takes destructive or unapproved actions | Muse cloud browser and Linux virtual machine ('Muse Secure VM') | | note(ノート) |
| 2026-11-10 | INEC Nigeria voter register: AI-generated photographs and duplicate records removed | AI used to run a cyber attack | | Investigation opened | Biometric Update |
| 2026-11-10 | Grok Build app share links exposed private user app data, including SpaceXSI internal material | Privacy harm to a person | Grok Build | Access removed, Publicly disclosed, Product or feature pulled | 36Kr |
| 2026-11-10 | Notion AI chat transcripts exposed via Fireworks AI vendor security incident | AI system attacked or breached | | Access removed, New monitoring put in place, Affected people told, Product or feature pulled | BleepingComputer |
| 2026-11-10 | Fireworks AI: unauthorized use of internal credentials in October, with API keys and tokens read from evaluation jobs | AI system attacked or breached | | Access removed, New monitoring put in place | news.lavx.hu |
| 2026-11-10 | Threat actor's self-running FOFA scanner harvests exposed OpenAI and DeepSeek API keys | Credential and privilege abuse | | | Cyber Security News |
| 2026-11-10 | Fireworks AI: October 23-24 breach via third-party cloud provider | AI system attacked or breached | | Access removed, Investigation opened, Flaw fixed, Affected people told | BleepingComputer |
| 2026-11-10 | NEAR AI security incident: SGLang remote code execution exposes user and legacy agent data | AI system attacked or breached | | Access removed, Flaw fixed, Affected people told, Product or feature pulled | Bitcoin.com News |
| 2026-11-10 | CDG autonomous shuttle stops in Punggol yellow box; software being adjusted | Physical harm | | Flaw fixed | STOMP |