Corrections
A published case is never edited. Every change makes a new version and is listed here with its reason, newest first. JSON
744 changes to 213 cases; the latest was on 2026-10-25.
Reviewer corrections 357Rebuilt from sources 112Merges of duplicates 91Other changes 87Fields added by a model 40Retractions 34Confidence grades lowered 21Name spelling 2
| Date | Case | What changed | By |
|---|---|---|---|
| 2026-10-18 | Character.AI chatbots promoted as therapists/psychologists; states cite 2024 wrongful-death suit and privacy concerns in bankruptcy filing LR-2026-0207 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | ARTEX AI pentesting agent used to breach 16 South Korean financial firms LR-2026-0206 · version 2 → 3 | Severity reason printed the whole rubric; source gives a bound, not an exact count. What was changed: citations, notes on gaps, confidence grades, records exposed and 1 more | Srini Iyer |
| 2026-10-18 | AI testing agents breached live systems of Indian firms, CERT-In says LR-2026-0204 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Multistate consumer-protection lawsuits against OpenAI over ChatGPT harms to children and adults LR-2026-0203 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Indirect prompt injection attempts embedded in HTTP response headers across websites LR-2026-0202 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | AI agent deletes entire season of Swedish reality show from production server LR-2026-0199 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Agentic AI bots attempt unauthorised access to Indian government websites LR-2026-0198 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Tencent Cloud agent fleet probes Alibaba Amap mapping service for over a week LR-2026-0197 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Anthropic Claude models bypass task restrictions and reach live police tip form LR-2026-0195 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Backdoored open-weight model exfiltrates project credentials through OpenAI Codex CLI LR-2026-0192 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Agents bypass newspapers.com paywall and Cloudflare bot check via urlquery.net and proxy services LR-2026-0191 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Waymo robotaxi maneuvers around stopped, unloading school bus in Atlanta LR-2026-0188 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Waymo robotaxi strikes and kills cat KitKat in San Francisco LR-2026-0187 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | The Challenge Sverige finished edit lost after production server failure; AI agent deletion alleged but denied LR-2026-0185 · version 2 → 3 | Absorbed LR-2026-0186, LR-2026-0200; severity reason printed the whole rubric. | Srini Iyer |
| 2026-10-18 | Aoki infostealer harvests AI coding assistant credentials and session files LR-2026-0183 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | AI agent-driven cyberattacks on 16 South Korean financial firms expose ~100,000 personal records LR-2026-0180 · version 2 → 3 | Severity reason printed the whole rubric; source gives a bound, not an exact count. What was changed: citations, notes on gaps, confidence grades, records exposed and 1 more | Srini Iyer |
| 2026-10-18 | Tesla robotaxi stuck playing fart sounds during paid ride; safety driver unable to stop it LR-2026-0179 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | OpenAI employee plants hidden recording device in office; AI models used to trace it LR-2026-0178 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | AI agent gains unauthorized access to Australian Government Medicare statistics portal LR-2026-0177 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | NHTSA petition case DP26010 over Tesla robotaxi speeding in school zones LR-2026-0173 · version 2 → 3 | Absorbed LR-2026-0174. | Srini Iyer |
| 2026-10-18 | AI deepfake ads depicting Wisconsin congressional candidate Rebecca Cooke LR-2026-0169 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | CyberXero AI-augmented initial access campaign using Claude Code and PentAGI agents LR-2026-0168 · version 2 → 3 | Severity reason printed the whole rubric; source gives a bound, not an exact count. What was changed: citations, notes on gaps, confidence grades, records exposed and 1 more | Srini Iyer |
| 2026-10-18 | Fideuram (Intesa Sanpaolo private banking) deepfake voice/video executive impersonation fraud LR-2026-0167 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Rogue OpenAI agents made unauthorized Wikipedia edits and millions of requests to Wikimedia LR-2026-0160 · version 2 → 3 | Source gives only the month. What was changed: precision of the date it occurred, notes on gaps | Srini Iyer |
| 2026-10-18 | Anthropic agents submitted 20 incomplete visa applications on State Department website LR-2026-0156 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Claude Haiku 4.5 submits fabricated homicide tip to police department web form LR-2026-0155 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | ComfyUI image-generation server compromised via exposed management interface; cryptominer installed LR-2026-0154 · version 3 → 4 | Severity reason printed the whole rubric; source gives only the month. What was changed: precision of the date it occurred, notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | AgentCorruption: prompt-injected Bedrock AgentCore agent exfiltrates execution-role credentials via IMDS LR-2026-0153 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Anthropic AI agent sends fabricated murder tip to Philadelphia Police LR-2026-0152 · version 2 → 3 | Absorbed LR-2026-0163, LR-2026-0164, LR-2026-0172; severity reason printed the whole rubric. | Srini Iyer |
| 2026-10-18 | Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites LR-2026-0150 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Astra agent fails to find Lean4 set-theory embedding after ~25h and several thousand dollars LR-2026-0149 · version 3 → 4 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | US intelligence chatbot fabricated Chinese nuclear vessel intelligence LR-2026-0148 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Kentucky Attorney General lawsuit against Character.AI over chatbots advising self-harm and suicide LR-2026-0147 · version 2 → 3 | Absorbed LR-2026-0162, LR-2026-0170; severity reason printed the whole rubric. | Srini Iyer |
| 2026-10-18 | AI agent (ARTEX with Claude) used in cyberattacks targeting South Korean banks LR-2026-0140 · version 2 → 3 | Absorbed LR-2026-0128, LR-2026-0134, LR-2026-0141, LR-2026-0144, LR-2026-0146, LR-2026-0159, LR-2026-0171; severity reason printed the whole rubric. | Srini Iyer |
| 2026-10-18 | DB-GPT 0.8.0 unauthenticated RCE via sandbox fallback and skill_upload directory traversal (CVE-2026-51862, CVE-2026-51869) LR-2026-0138 · version 3 → 4 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Meta Muse AI agent KVM escape vulnerability discovered before launch LR-2026-0137 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Autonomous AI agent framework (Strix/Cairn/Hermes) used to attack hundreds of online retailers and steal card data LR-2026-0133 · version 2 → 3 | Severity reason printed the whole rubric; source gives a bound, not an exact count. What was changed: citations, notes on gaps, confidence grades, why this severity and 1 more | Srini Iyer |
| 2026-10-18 | AI coding agent powered by Anthropic's Claude on the PocketOS developer platform wiped the production database and three months of backups LR-2026-0132 · version 2 → 3 | Severity reason printed the whole rubric; title described a different event than the record. What was changed: notes on gaps, why this severity, title | Srini Iyer |
| 2026-10-18 | Shinhan Bank data breach with suspected AI-assisted intrusion LR-2026-0127 · version 2 → 3 | Source gives a bound, not an exact count. What was changed: citations, notes on gaps, confidence grades, records exposed and 1 more | Srini Iyer |
| 2026-10-18 | Claude Code agent deletes 48,218 Windows project files and damages Git object store LR-2026-0126 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
Showing 481–520 of 744 · page 13 of 19. ‹ Previous · Next › Or take the JSON.