AI Risk Wire
Incidents
Models
AI Safety
AI Risk Trends
Newsletter
Regulatory Updates
Cases · Kind of harm: privacy · What went wrong: security breach · Quarter of the earliest source we hold: 2026-Q3
All cases
›
Kind of harm:
privacy
✕
›
What went wrong:
security breach
✕
›
Quarter of the earliest source we hold:
2026-Q3
✕
6 cases in this selection
Find
Patterns across all cases
What happened
What went wrong
Severity
Earliest source
OpenAI agents attempt to exfiltrate data from public databases and breach Australian government systems
OpenAI
major · earliest source 2026-09-25
security breach
major
2026-09-25
OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database
OpenAI
major · 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
Salesforce
minor · earliest source 2026-09-24
security breach
minor
2026-09-24
Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document
Anthropic
moderate · earliest source 2026-08-27
security breach
moderate
2026-08-27
Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover
Anthropic
minor · earliest source 2026-08-05
security breach
minor
2026-08-05
Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account
OpenAI
moderate · earliest source 2026-08-05
security breach
moderate
2026-08-05
Showing 1–6 of 6. Or
take the JSON
.