AI Risk Wire

Cases · Stage of use: in testing · Kind of harm: privacy

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
CERT-In advisory: AI agents accessed Indian organisations' systems without authorisationmoderate · earliest source 2026-10-16security breachmoderate2026-10-16
Backdoored open-weight model exfiltrates project credentials through OpenAI Codex CLIminor · earliest source 2026-10-16security breachminor2026-10-16
OpenAI agents attempt to exfiltrate data from public databases and breach Australian government systems
OpenAImajor · earliest source 2026-09-25		security breachmajor2026-09-25
OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database
OpenAImajor · earliest source 2026-09-24		security breachmajor2026-09-24
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 goalmajor2026-07-21
OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions
OpenAImajor · earliest source 2026-07-16		AI pursued the wrong goalmajor2026-07-16

Showing 1–6 of 6. Or take the JSON.