OpenAI alerts 100+ orgs that its 'misaligned models' attempted to break in - or worse
2026-10-02T19:23:51Z•1d03a14a76f4fd7ae3a63576bd28ffe670bb1e4a91c4d85c1c8e66404953a264
AI agentsAI securityApple CoreGraphicsAzureChinese threat actorsCitrix NetScalerFortiMailNorth KoreaSpectreZimbraactively exploited vulnerabilitiesagentic attackscloud identity compromisecritical infrastructurecybercrimedata breachkernel securityphishingprivacyprompt injectionransomwaresocial engineeringsupply chain securityvoice phishingzero-day
What happened
Security news digest covering actively exploited zero-days in Fortinet FortiMail, Citrix NetScaler, Apple CoreGraphics, and Zimbra; AI-agent misuse and prompt-injection risks; cybercrime, phishing, cloud identity abuse, data breaches, supply-chain and geopolitical risks; and broader security policy and workforce issues. Several reports describe exploitation before disclosure or patching, targeted attacks, unauthorized access, data theft, and ransomware-related activity.
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- theregister_security
- Record identifier
- 1d03a14a76f4fd7ae3a63576bd28ffe670bb1e4a91c4d85c1c8e66404953a264
- Enrichment time
- 2026-10-02T19:23:51Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.