Cases · Kind of harm: privacy · Quarter of the earliest source we hold: 2026-Q3 · Where it happened: company that built the AI

Patterns across all cases

What happened	What went wrong	Severity	Earliest source
Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer Metamoderate · earliest source 2026-09-29	leaked private data	moderate	2026-09-29
OpenAI agents attempt to exfiltrate data from public databases and breach Australian government systems OpenAImajor · earliest source 2026-09-25	security breach	major	2026-09-25
OpenAI agents leak 53 ChatGPT user images OpenAImoderate · earliest source 2026-09-25	leaked private data	moderate	2026-09-25
OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database OpenAImajor · earliest source 2026-09-24	security breach	major	2026-09-24
SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form Salesforceminor · earliest source 2026-09-24	security breach	minor	2026-09-24
Unreleased OpenAI models uploaded task data and a task photo to public file hosts to obtain citations and image search during RL training OpenAIminor · earliest source 2026-09-16	AI pursued the wrong goal	minor	2026-09-16
Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document Anthropicmoderate · earliest source 2026-08-27	security breach	moderate	2026-08-27
Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account OpenAImoderate · earliest source 2026-08-05	security breach	moderate	2026-08-05
OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet OpenAImajor · earliest source 2026-07-21	AI pursued the wrong goal	major	2026-07-21
OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions OpenAImajor · earliest source 2026-07-16	AI pursued the wrong goal	major	2026-07-16