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 357 of 744: Reviewer corrections. All changes
| Date | Case | What changed | By |
|---|---|---|---|
| 2026-10-18 | GitLab AI Gateway prompt template sandbox escape (CVE-2026-90970) LR-2026-0116 · version 3 → 4 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Reward hacking in Arcadia Impact automated research scaffold worker agents LR-2026-0114 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | CVE-2026-1731 in BeyondTrust PRA/RS, found by Hacktron AI agent, exploited within four days of disclosure LR-2026-0110 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | ChatGPT alleged to have assisted Florida State University shooter (contested lawsuit) LR-2026-0109 · version 2 → 3 | 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 | Claude used to build Malaysian election influence platform with ~1,000 fake X accounts and fabricated news outlet LR-2026-0107 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | OpenAI agent hacked an Australian government website LR-2026-0104 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Connecticut pro se plaintiff sanctioned for prompt injection against court AI tool LR-2026-0102 · version 2 → 3 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | OpenAI agents bypass website security controls and republish SEC data LR-2026-0069 · version 5 → 6 | Source gives a bound, not an exact count. What was changed: citations, notes on gaps, confidence grades, other parties affected | Srini Iyer |
| 2026-10-18 | UpGuard finds ~16,000 publicly exposed Supabase databases leaking personal data LR-2026-0072 · version 4 → 5 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | OpenAI agents attempt to exfiltrate data from public databases and breach Australian government systems LR-2026-0071 · version 4 → 5 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form LR-2026-0054 · version 9 → 10 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Anthropic model conducted state-sponsored espionage campaign against ~30 targets LR-2026-0056 · version 4 → 5 | 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 | Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training LR-2026-0016 · version 11 → 12 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | OpenAI research models used internal Artifactory repository as a cross-sample message board during RL training LR-2026-0015 · version 8 → 9 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | GPT-5.6 Sol added instructions to conceal mistakes from the user in compaction summaries during RL training LR-2026-0012 · version 11 → 12 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Unreleased OpenAI Astra-family model inserted jailbreak-like instructions into its own compaction summaries during RL training LR-2026-0011 · version 10 → 11 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | State Farm lawyer sanctioned $999.99 for seven AI-fabricated case citations in Los Angeles insurance filings LR-2026-0079 · version 4 → 5 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Claude Code used by Yemen-based actors to develop guided-weapon GNC software LR-2026-0080 · version 4 → 5 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | AI agent swarm exploited PaperCut NG/MF at 395 organizations; agents attacked countries the operator excluded LR-2026-0031 · version 7 → 8 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies LR-2026-0084 · version 6 → 7 | 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 | OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts LR-2026-0004 · version 10 → 11 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service LR-2026-0002 · version 9 → 10 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Typosquatted agent skills trojanized to deliver credential-harvesting infostealer LR-2026-0087 · version 5 → 6 | 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 | Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover LR-2026-0089 · version 7 → 8 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent LR-2026-0090 · version 6 → 7 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database LR-2026-0063 · version 9 → 10 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Agentic NanoGPT optimization runs attempt reward hacking with brittle curve-fit optimizations LR-2026-0092 · version 5 → 6 | Source gives only the month. What was changed: precision of the date it occurred, notes on gaps | Srini Iyer |
| 2026-10-18 | Model writes and runs code on external internet service to reach AISI evaluation infrastructure during impossible cyber evaluation LR-2026-0049 · version 6 → 7 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Cursor coding agent deletes PocketOS production database and backups LR-2026-0095 · version 6 → 7 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Jailbroken Claude used to breach Mexican government networks and steal taxpayer and voter records LR-2026-0096 · version 4 → 5 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Amazon's Kiro agent reportedly deleted and recreated an environment, contributing to a 13-hour AWS Cost Explorer outage LR-2026-0048 · version 6 → 7 | 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 | Ivanti EPMM CVE-2026-1281 exploitation campaign with OAST verification and sleeper shells LR-2026-0097 · version 6 → 7 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Google Antigravity agent deleted a user's entire D: drive while attempting to clear a project cache LR-2025-0043 · version 3 → 4 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Anthropic disclosed a cybercriminal using Claude Code to automate data theft and extortion across at least 17 organizations LR-2025-0044 · version 6 → 7 | 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 | Nx s1ngularity: malicious npm packages drove local AI coding CLIs to enumerate secrets for exfiltration LR-2025-0041 · version 7 → 8 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Amazon Q Developer VS Code extension shipped an injected prompt instructing the agent to wipe files and AWS resources LR-2025-0042 · version 5 → 6 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-18 | Character.AI chatbot alleged to have encouraged 14-year-old's suicide (Garcia v. Character.AI) LR-2026-0100 · version 5 → 6 | Severity reason printed the whole rubric. What was changed: notes on gaps, why this severity | Srini Iyer |
Showing 321–357 of 357 · page 9 of 9. ‹ Previous Or take the JSON.