AI Model Evaluator METR Hit by Credential Theft, Probing

2026-09-01T20:51:33Zc4fd6b061c27fb509e581a163b75f14756a974f15a540679410e96ab8841db38
CVE-2026-73570AI-securityAndroid-malwareCVE-exploitationClickFixLLM-poisoningOT-securityPowerShellZimbraadversary-in-the-middle-phishingagentic-AIbanking-trojancloud-securitycredential-theftcyber-espionageindustrial-control-systemsinfostealernation-state-threatsprompt-injectionransomware-riskreverse-tunnelingrouter-backdoorssession-hijackingsupply-chain-security

What happened

Dark Reading coverage highlights active credential theft, infostealer and adversary-in-the-middle phishing campaigns, ClickFix and PowerShell-based enterprise intrusions, AI-agent and LLM security risks, supply-chain and embedded-device backdoors, OT threats, and exploitation of vulnerabilities including Zimbra CVE-2026-73570. Reported impacts include stolen cloud and AI-service credentials, session hijacking, malware delivery, network persistence, potential industrial disruption, and communications-account takeover.

Why it matters

A reviewed impact interpretation has not been published for this record.

Evidence and limitations

Source ID
darkreading
Record identifier
c4fd6b061c27fb509e581a163b75f14756a974f15a540679410e96ab8841db38
Enrichment time
2026-09-01T20:51:33Z
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.