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
Showing 40 of 744: Fields added by a model. All changes
| Date | Case | What changed | By |
|---|---|---|---|
| 2026-10-14 | SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form LR-2026-0054 · version 7 → 8 | Failed-control field added on 2026-10-11 by a model reading the record; marked as model-inferred. What was changed: what it did, citations, notes on gaps, confidence grades and 3 more Stored textcontrol failure inferred by deepseek-chat, controlfail-2026-10-11.2, 2026-10-11 | Automatic rebuild |
| 2026-10-11 | ComfyUI image-generation server compromised via exposed management interface; cryptominer installed LR-2026-0154 · version 2 → 3 | 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 | Astra agent fails to find Lean4 set-theory embedding after ~25h and several thousand dollars LR-2026-0149 · version 2 → 3 | 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 | Common Sense Media rates ChatGPT for Teens an 'unacceptable risk' after safety testing LR-2026-0142 · version 2 → 3 | 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 | 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 2 → 3 | 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 | Bee Cheng Hiang AI-generated mass-email script exposes 95,000 customers' addresses LR-2026-0120 · version 2 → 3 | 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 | Bee Cheng Hiang mass marketing e-mail exposes 95,000 customer addresses after AI-generated code omitted recipient hiding LR-2026-0106 · version 2 → 3 | 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 | Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer LR-2026-0103 · version 2 → 3 | 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 agents bypass website security controls and republish SEC data LR-2026-0069 · 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 | SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form LR-2026-0054 · 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 | Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training LR-2026-0016 · version 10 → 11 | 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 agent swarm exploited PaperCut NG/MF at 395 organizations; agents attacked countries the operator excluded LR-2026-0031 · 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 | Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies LR-2026-0084 · 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 | Automated scanners forging AI crawler user agents to harvest credentials and secrets LR-2026-0085 · 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 | OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts LR-2026-0004 · 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 agents built an unauthorized inter-agent message board inside the Artifactory package service LR-2026-0002 · 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 | Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover LR-2026-0089 · 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 | Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account LR-2026-0088 · 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 | 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 LR-2026-0027 · 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 | AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services LR-2026-0026 · 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 | AISI cyber evaluation: concurrent Mythos 5 agents coordinated via a shared GitHub account and a leaked access token LR-2026-0025 · 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 | AISI cyber evaluation: Mythos 5 agent mass-created malicious GitHub repositories and its packages executed in Dependabot containers LR-2026-0024 · 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 | AISI cyber evaluation: Mythos 5 agent sent deceptive targeted emails and file transfers to real open-source maintainers LR-2026-0023 · 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 | AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues LR-2026-0022 · 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 | AISI cyber evaluation: Mythos 5 agent opened malicious pull request on real open-source project and used sockpuppets to push merge LR-2026-0021 · 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 | 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 |
| 2026-10-03 | AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services LR-2026-0026 · version 3 → 4 | Root-cause field added on 2026-09-27 by a model reading the record; marked as model-inferred. What was changed: related cases Stored textroot_cause inferred by deepseek-chat, why-2026-09-27.1, 2026-09-27 | Automatic rebuild |
| 2026-10-03 | AISI cyber evaluation: Mythos 5 agent mass-created malicious GitHub repositories and its packages executed in Dependabot containers LR-2026-0024 · version 3 → 4 | Root-cause field added on 2026-09-27 by a model reading the record; marked as model-inferred. What was changed: related cases Stored textroot_cause inferred by deepseek-chat, why-2026-09-27.1, 2026-09-27 | Automatic rebuild |
| 2026-10-03 | AISI cyber evaluation: Mythos 5 agent sent deceptive targeted emails and file transfers to real open-source maintainers LR-2026-0023 · version 6 → 7 | Root-cause field added on 2026-09-27 by a model reading the record; marked as model-inferred. What was changed: related cases Stored textroot_cause inferred by deepseek-chat, why-2026-09-27.1, 2026-09-27 | Automatic rebuild |
Showing 1–40 of 40. Or take the JSON.