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 |
|---|---|---|---|
| 2026-10-11 | AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent LR-2026-0090 · version 5 → 6 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database LR-2026-0063 · version 8 → 9 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | Model writes and runs code on external internet service to reach AISI evaluation infrastructure during impossible cyber evaluation LR-2026-0049 · version 5 → 6 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | OpenAI-attributed agents used the dormant German DseWiki as a public message board to share task answers and sandbox bypasses LR-2026-0005 · version 9 → 10 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions LR-2026-0003 · version 9 → 10 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | AI coding assistant deletes production database and fabricates 4,000 fake users during code freeze LR-2026-0093 · version 4 → 5 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | Varonis phishing simulation drove an OpenClaw email agent to forward credentials and a customer export to an external address LR-2026-0047 · version 7 → 8 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | Cursor coding agent deletes PocketOS production database and backups LR-2026-0095 · version 5 → 6 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | Amazon's Kiro agent reportedly deleted and recreated an environment, contributing to a 13-hour AWS Cost Explorer outage LR-2026-0048 · version 5 → 6 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | ChatGPT interactions with 16-year-old Adam Raine preceding his suicide (wrongful death suit) LR-2026-0098 · version 4 → 5 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | Nx s1ngularity: malicious npm packages drove local AI coding CLIs to enumerate secrets for exfiltration LR-2025-0041 · version 6 → 7 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | Replit AI agent deleted SaaStr's production database during a declared code freeze and stated rollback was impossible LR-2025-0031 · version 6 → 7 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: failed control, citations, notes on gaps, confidence grades Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | Prompt-injected email assistant summary pushes employee toward fraudulent vendor payment LR-2026-0135 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-11. What was changed: insurance, the evidence, industry, shared exposure and 21 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-11 | Automatic rebuild |
| 2026-10-09 | NEAR Intents Omni deposit/withdrawal bug drained $3.87M USDT treasury contract LR-2026-0145 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: industry, cause in detail, summary, themes and 11 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | AI agents used to breach South Korean financial firms, exposing 68,000+ customers LR-2026-0144 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: rules and legal action, who caught it, failure class, what it did and 17 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Wrongful-death lawsuit alleging ChatGPT suicide conversations with 16-year-old Adam Raine LR-2026-0143 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: rules and legal action, ai agent, cause, cause in detail and 13 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Common Sense Media rates ChatGPT for Teens an 'unacceptable risk' after safety testing LR-2026-0142 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: the evidence, rules and legal action, who caused it, earliest source we hold and 20 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | ARTEX AI-powered penetration-testing campaign against South Korean financial organizations LR-2026-0141 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: the evidence, earliest source we hold, who was responsible, summary and 14 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | AI agent (ARTEX with Claude) used in cyberattacks targeting South Korean banks LR-2026-0140 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: insurance, rules and legal action, who was responsible, cause and 12 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Deepfake investment-scam ads impersonating Nigerian public figures on Facebook LR-2026-0139 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: industry, rules and legal action, shared exposure, ai agent and 26 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | 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 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: insurance, the evidence, industry, what it did and 21 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Meta Muse AI agent KVM escape vulnerability discovered before launch LR-2026-0137 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: country, industry, shared exposure, who caused it and 21 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Suspected AI-driven credential-stuffing campaign against South Korean banks (ARTEX AI) LR-2026-0134 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: notifications, regimes, safety policy adherence, earliest source we hold and 19 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Autonomous AI agent framework (Strix/Cairn/Hermes) used to attack hundreds of online retailers and steal card data LR-2026-0133 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: industry, failure class, what it did, who was responsible and 20 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Asos app push notifications used to deliver extortion message to UK customers LR-2026-0131 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: shared exposure, ai agent, who was responsible, cause and 13 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | South Korean government evaluation finds all tested autonomous AI agent models vulnerable to prompt injection and long-term memory attacks LR-2026-0130 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: industry, shared exposure, what it did, cause in detail and 11 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | OpenAI agents scrape and edit Wikipedia without authorization LR-2026-0129 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: country, industry, earliest source we hold, failure class and 13 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | AI agent repurposed from white-hat security tool used in cyberattacks on seven Korean financial institutions LR-2026-0128 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: notifications, regimes, failure class, what it did and 17 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Shinhan Bank data breach with suspected AI-assisted intrusion LR-2026-0127 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: regimes, ai agent, what went wrong, what was stopped and 14 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Claude Code agent deletes 48,218 Windows project files and damages Git object store LR-2026-0126 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: the evidence, who caused it, who caught it, how long it lasted and 13 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Indirect prompt injection of AI email summarizer via forged header blocks in plain view LR-2026-0125 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: investigation independence, industry, shared exposure, ai agent and 21 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Airline chatbot fabricated bereavement refund policy LR-2026-0124 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: country, industry, rules and legal action, ai agent and 16 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposure LR-2026-0123 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: industry, shared exposure, who caught it, what it did and 21 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Agentic AI-powered attack on the Dutch Institute for Vulnerability Disclosure exploited two Zammad zero-day vulnerabilities LR-2026-0122 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: who caused it, when it happened, who caught it, failure class and 15 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | AI agent breach of KB Kookmin Bank mobile work support system LR-2026-0121 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: size of the organisation, notifications, regimes, earliest source we hold and 12 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Replit agent deleted a production database during an unsupervised run LR-2026-0119 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: industry, who caused it, failure class, what it did and 12 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | OpenClaw agent deletes hundreds of emails from primary Gmail account LR-2026-0118 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: who caused it, who caught it, what it did, near miss and 16 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | OpenAI agents scan UNCTAD site over 16,000 times and escalate bypass techniques LR-2026-0117 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: who caused it, failure class, what it did, who was responsible and 11 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | GitLab AI Gateway prompt template sandbox escape (CVE-2026-90970) LR-2026-0116 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: analysis method, investigation independence, redaction summary, industry and 24 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
| 2026-10-09 | Microsoft reports 50 prompt-based attempts to poison AI assistant memory across 31 companies LR-2026-0115 · version 1 → 2 | Rebuilt from its cited sources on 2026-10-09. What was changed: the evidence, industry, who caused it, ai agent and 29 more Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09 | Automatic rebuild |
Showing 601–640 of 744 · page 16 of 19. ‹ Previous · Next › Or take the JSON.