| VAID-2026-0042 |
2 |
2026-08-30 |
Codex user reports unauthorized WhatsApp sends and forged approvals during development
DECSCBUNA OpenAI Codex desktop app on Windows with an internal subagent; exact version not supplied · Not established — America/Santiago is the reported session timezone, not verified physical location |
software engineering |
reported |
| VAID-2026-0032 |
3 |
2026-04 (day unknown) |
Cursor agent deletes PocketOS database volume; Railway subsequently restores all data
UNA Cursor agent, reported as using Claude Opus 4.6, with an account-scoped Railway token |
software engineering |
reported |
| VAID-2026-0041 |
4 |
2026-02-22 |
Lobstar Wilde transfers a large token position to a social-media requester
UNA Lobstar Wilde, Nik Pash's personal AI trading-agent experiment |
finance |
reported |
| VAID-2026-0040 |
2 |
2026-02-11 |
MJ Rathbun publishes a personal attack after a matplotlib pull request is rejected
DECUNA MJ Rathbun, an OpenClaw agent; specific model at the time not established |
software engineering |
reported |
| VAID-2026-0031 |
1 |
2026-02 (day unknown) |
Unit 42 identifies malicious and agentic-fraud skills on ClawHub
DEXEXMUNA OpenClaw agents using third-party ClawHub skills |
software engineering |
reported |
| VAID-2025-0026 |
3 |
2025-09 (day unknown) |
Anthropic reports Claude Code use in the GTG-1002 espionage campaign
DEXEXMSCBUNA Claude Code used within an attacker-built framework |
defence |
reported |
| VAID-2025-0024 |
3 |
2025-08-26 |
Nx supply-chain malware uses AI CLIs for supplementary file discovery
DEXEXMUNA Malicious Nx packages; attempted use of local Claude Code, Gemini CLI and Amazon Q |
software engineering |
reported |
| VAID-2025-0014 |
2 |
2025-04 (day unknown) |
Cursor support bot invents a one-device subscription policy
DEC Cursor's front-line AI email-support bot, identified as Sam |
software engineering |
reported |
| VAID-2025-0038 |
2 |
2025-02 (day unknown) |
OpenAI Operator buys eggs without approval during a price comparison
UNA OpenAI Operator research preview |
consumer |
reported |
| VAID-2024-0012 |
0 |
2024-11 (day unknown) |
Freysa adversarial contest ends in a prize-pool transfer
EXM Freysa, an AI-controlled prize-pool game on Base |
finance |
reported |
| VAID-2024-0011 |
0 |
2024-10-11 |
Truth Terminal promotes GOAT following engagement by human token holders
EXM Truth Terminal; multiple models, primarily Llama 3.1 according to its operator |
finance |
reported |
| VAID-2024-0007 |
2 |
2024-03 (day unknown) |
Tests find incorrect legal guidance from New York City's MyCity chatbot
DEC MyCity business chatbot, powered by Microsoft Azure AI services · New York, NY, US |
government |
reported |
| VAID-2024-0006 |
1 |
2024-01-18 |
User elicits profanity and criticism from DPD's support chatbot
EXM DPD support chatbot's AI component; model not established · United Kingdom |
consumer |
reported |
| VAID-2023-0005 |
1 |
2023-12-17 |
User prompts a dealership chatbot into a purported $1 vehicle offer
EXM Fullpath ChatGPT-powered chatbot at Chevrolet of Watsonville · Watsonville, CA, US |
consumer |
reported |
| VAID-2025-0039 |
2 |
Not established |
ROME training agent opens an external tunnel and diverts GPUs to cryptocurrency mining
SCBUNA ROME agentic model in reinforcement-learning training |
research |
reported |
| VAID-2026-0037 |
1 |
Not established |
Contract-review LLM service follows injected instruction and discloses its system prompt
DEXEXM Unnamed self-hosted contract-risk analysis service built on an open-weight model of roughly nine billion parameters (8192-token context); model and framework deliberately not named by the author |
software engineering |
reported |
| VAID-2025-0018 |
0 |
Not established |
Anthropic documents agentic misalignment in simulated companies
DECUNA 16 models from several developers, including Anthropic, OpenAI, Google, Meta and xAI · research environment |
research |
reported |
| VAID-2025-0016 |
0 |
Not established |
Reasoning models interfere with shutdown scripts in Palisade tests
LOCSCB OpenAI o3, o4-mini and codex-mini, with other models tested for comparison · research environment |
research |
reported |
| VAID-2024-0013 |
0 |
Not established |
Apollo Research documents scheming in controlled agent evaluations
DECSCB o1, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro and Llama 3.1 405B · research environment |
research |
reported |
| VAID-2024-0009 |
2 |
Not established |
AI Scientist experiments spawn uncontrolled processes and attempt runtime extensions
SCBSRP The AI Scientist, developed by researchers affiliated with Sakana AI, Oxford and UBC · Tokyo, JP |
research |
reported |
| VAID-2024-0008 |
2 |
Not established |
Reports of order-taking errors during McDonald's IBM AI pilot
IBM Automated Order Taking voice-recognition system · United States (100+ restaurants) |
consumer |
reported |