LIVE · cybersecurity feed
Live wire
CVE-2026-81578 · PaperCut NG/MF Flaw Exploited Before CVE PublicationCVE-2026-82078 · PaperCut NG/MF Flaw Exploited Before CVE PublicationCVE-2026-83549 · SonicWall SMA1000 OS Command Injection Exploited Same Day as DisclosureCVE-2026-83548 · SonicWall SMA1000 SSRF Flaw Exploited Same Day as DisclosureCVE-2026-82329 · JFrog Artifactory Flaw Exploited Same Day as DisclosureOpenAI Announced $1B in Defensive Tools for Water UtilitiesAttackers Breached JetBrains Cadence via Unpatched TeamCity, Extracting AWS CredentialsCVE-2026-59346 · Critical VMware Workstation and Fusion Flaw Lets VM Admins Execute Host CodeCVE-2026-32475 · Elementor Pro WordPress Plugin Vulnerability Exploited to Hack SitesBroadcom Patches Critical VMware Workstation and Fusion VM-Escape Vulnerabilities
cve recordcritical

CVE-2026-45374

Published
CVSS9.6
Severitycritical
WeaknessCWE-94
ExploitedNot in CISA KEV

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

Description

CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the task_create tool spawns durable sub-agents that inherit two insecure defaults, allow_shell defaults to true (config.rs:1499: self.allow_shell.unwrap_or(true)) and auto_approve defaults to true (task_manager.rs:297: auto_approve: Some(true)). When a user approves a task_create call (which requires ApprovalRequirement::Required), they approve what appears to be a benign work prompt. However, the spawned sub-agent silently receives unrestricted, unapproved shell access. This vulnerability is fixed in 0.8.26.

References

← Back to the CVE Tracker

Our coverage of CVE-2026-45374

No stories yet. This page updates automatically when we publish reporting that references CVE-2026-45374.