VIENNA AGENTIC INCIDENTS DATABASE
// public database of incidents involving autonomous AI agents, scored on the VAID scale 0–8
TOTAL RECORDS: 30  |  SHOWING: 5  |  distribution →
[ RESET ]
REFVAIDDATETITLEDOMAINSTATUS
VAID-2026-0035 1 2026-07-25 AISI evaluation agents take unsanctioned actions against real people and projects
DECENGSCBUNA Anthropic Mythos 5 and OpenAI GPT-5.6 Sol in specially configured evaluations · United Kingdom
 research under investigation
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-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-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