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 |
|---|---|---|---|
| 2026-10-22 | Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposure LR-2026-0123 · version 2 → 3 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, who was responsible, citations, notes on gaps and 1 more | Srini Iyer |
| 2026-10-22 | AI agent breach of KB Kookmin Bank mobile work support system LR-2026-0121 · version 4 → 5 | A judgement inferred by us that no source states was cleared. What was changed: citations, notes on gaps, confidence grades, can it be undone | Srini Iyer |
| 2026-10-22 | OpenClaw agent deletes hundreds of emails from primary Gmail account LR-2026-0118 · version 3 → 4 | A judgement inferred by us that no source states was cleared. What was changed: cause in detail, citations, notes on gaps, confidence grades and 1 more | Srini Iyer |
| 2026-10-22 | GitLab AI Gateway prompt template sandbox escape (CVE-2026-90970) LR-2026-0116 · version 5 → 6 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, who was responsible, cause, cause in detail and 3 more | Srini Iyer |
| 2026-10-22 | Reward hacking in Arcadia Impact automated research scaffold worker agents LR-2026-0114 · version 4 → 5 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, cause, cause in detail, citations and 2 more | Srini Iyer |
| 2026-10-22 | OpenAI cancels GPT-6.1 Astra release after model took actions without permission during internal testing LR-2026-0112 · version 3 → 4 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, cause in detail, citations, notes on gaps and 1 more | Srini Iyer |
| 2026-10-22 | Guardian test: ChatGPT and Grok remove hijab from AI-generated image of Muslim woman LR-2026-0108 · version 2 → 3 | A judgement inferred by us that no source states was cleared; citations to sentences about a different event were removed; summary or story described a different event or the article, not this event. What was changed: shared exposure, who was responsible, cause, cause in detail and 4 more | Srini Iyer |
| 2026-10-22 | AI-generated sexually explicit deepfake smear campaign against Porsche sales consultant Mu Qianwen LR-2026-0105 · version 2 → 3 | A judgement inferred by us that no source states was cleared. What was changed: who was responsible, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer LR-2026-0103 · version 4 → 5 | A judgement inferred by us that no source states was cleared. What was changed: citations, notes on gaps, confidence grades, can it be undone | Srini Iyer |
| 2026-10-22 | OpenAI agents bypass website security controls and republish SEC data LR-2026-0069 · version 8 → 9 | A judgement inferred by us that no source states was cleared; an event recorded in another case was counted here; severity now rests on this case's own event; citations to sentences about a different event were removed. What was changed: shared exposure, near miss, who was responsible, cause and 12 more | Srini Iyer |
| 2026-10-22 | OpenAI agents leak 53 ChatGPT user images LR-2026-0068 · version 6 → 7 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, who was responsible, citations, notes on gaps and 1 more | Srini Iyer |
| 2026-10-22 | OpenAI agents attempt to exfiltrate data from public databases and breach Australian government systems LR-2026-0071 · version 6 → 7 | A date that belongs to another event was replaced or cleared; a judgement inferred by us that no source states was cleared. What was changed: when it happened, cause, cause in detail, citations and 2 more | Srini Iyer |
| 2026-10-22 | LLM pipeline deanonymizes pseudonymous Hacker News and scientist accounts LR-2026-0061 · version 5 → 6 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, citations, notes on gaps, confidence grades and 1 more | Srini Iyer |
| 2026-10-22 | Zhipu ZCode repository snapshot upload without clear consent LR-2026-0050 · version 7 → 8 | A judgement inferred by us that no source states was cleared. What was changed: cause in detail, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | AEPD-confirmed autonomous AI agent data breach (Spain) LR-2026-0059 · version 6 → 7 | A judgement inferred by us that no source states was cleared. What was changed: cause in detail, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Frontier LLM agent fabricated a complete calibration-comparison report for commands that never ran LR-2026-0051 · version 5 → 6 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Google Gemini accessed systems of three real companies during a misconfigured third-party cybersecurity evaluation LR-2026-0033 · version 4 → 5 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, who was responsible, cause, cause in detail and 3 more | Srini Iyer |
| 2026-10-22 | Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training LR-2026-0016 · version 13 → 14 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, cause, cause in detail, citations and 2 more | Srini Iyer |
| 2026-10-22 | OpenAI research models used internal Artifactory repository as a cross-sample message board during RL training LR-2026-0015 · version 11 → 12 | A judgement inferred by us that no source states was cleared. What was changed: who was responsible, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Unreleased OpenAI models uploaded task data and a task photo to public file hosts to obtain citations and image search during RL training LR-2026-0014 · version 11 → 12 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, cause, cause in detail, citations and 2 more | Srini Iyer |
| 2026-10-22 | GPT-5.6 Sol added instructions to conceal mistakes from the user in compaction summaries during RL training LR-2026-0012 · version 13 → 14 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, who was responsible, cause, cause in detail and 3 more | Srini Iyer |
| 2026-10-22 | Unreleased OpenAI Astra-family model inserted jailbreak-like instructions into its own compaction summaries during RL training LR-2026-0011 · version 13 → 14 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, who was responsible, citations, notes on gaps and 2 more | Srini Iyer |
| 2026-10-22 | Claude Code used by Yemen-based actors to develop guided-weapon GNC software LR-2026-0080 · version 5 → 6 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, who was responsible, citations, notes on gaps and 1 more | Srini Iyer |
| 2026-10-22 | Agent swarm attributed to OpenAI published thousands of RubyGems packages, gained RCE on RubyDoc.info, and attempted API-key theft LR-2026-0032 · version 8 → 9 | A judgement inferred by us that no source states was cleared. What was changed: cause, cause in detail, citations, notes on gaps and 1 more | Srini Iyer |
| 2026-10-22 | AI agent swarm exploited PaperCut NG/MF at 395 organizations; agents attacked countries the operator excluded LR-2026-0031 · version 8 → 9 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies LR-2026-0084 · version 7 → 8 | A judgement inferred by us that no source states was cleared. What was changed: insurance, shared exposure, who was responsible, citations and 2 more | Srini Iyer |
| 2026-10-22 | Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document LR-2026-0086 · version 6 → 7 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, who was responsible, citations, notes on gaps and 2 more | Srini Iyer |
| 2026-10-22 | OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts LR-2026-0004 · version 14 → 15 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service LR-2026-0002 · version 13 → 14 | A date that belongs to another event was replaced or cleared; a judgement inferred by us that no source states was cleared; citations to sentences about a different event were removed. What was changed: when it happened, who was responsible, citations, notes on gaps and 1 more | Srini Iyer |
| 2026-10-22 | Typosquatted agent skills trojanized to deliver credential-harvesting infostealer LR-2026-0087 · version 6 → 7 | A judgement inferred by us that no source states was cleared. What was changed: cause, cause in detail, citations, notes on gaps and 1 more | Srini Iyer |
| 2026-10-22 | Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover LR-2026-0089 · version 8 → 9 | A judgement inferred by us that no source states was cleared; a value cited to a sentence about a different event or company was cleared; severity reason did not fit its quote or the record. What was changed: insurance, who was responsible, citations, notes on gaps and 4 more | Srini Iyer |
| 2026-10-22 | Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account LR-2026-0088 · version 7 → 8 | A judgement inferred by us that no source states was cleared; citations to sentences about a different event were removed; summary or story described a different event or the article, not this event. What was changed: insurance, shared exposure, who was responsible, cause and 5 more | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services LR-2026-0026 · version 9 → 10 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, who was responsible, citations, notes on gaps and 1 more | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: concurrent Mythos 5 agents coordinated via a shared GitHub account and a leaked access token LR-2026-0025 · version 14 → 15 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent mass-created malicious GitHub repositories and its packages executed in Dependabot containers LR-2026-0024 · version 9 → 10 | A judgement inferred by us that no source states was cleared. What was changed: who was responsible, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent sent deceptive targeted emails and file transfers to real open-source maintainers LR-2026-0023 · version 11 → 12 | A judgement inferred by us that no source states was cleared. What was changed: cause, cause in detail, citations, notes on gaps and 1 more | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues LR-2026-0022 · version 11 → 12 | A judgement inferred by us that no source states was cleared. What was changed: citations, notes on gaps, confidence grades, can it be undone | Srini Iyer |
| 2026-10-22 | 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 12 → 13 | A judgement inferred by us that no source states was cleared. What was changed: who was responsible, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training LR-2026-0013 · version 16 → 17 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, who was responsible, citations, notes on gaps and 1 more | Srini Iyer |
| 2026-10-22 | AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent LR-2026-0090 · version 7 → 8 | A judgement inferred by us that no source states was cleared. What was changed: shared exposure, who was responsible, citations, notes on gaps and 2 more | Srini Iyer |
Showing 201–240 of 744 · page 6 of 19. ‹ Previous · Next › Or take the JSON.