Skip to content

CVE-2026-45374 CodeWhale: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files

CriticalCVSS 9.6 EPSS 0.39%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
Proof of concept public · automatable: no · technical impact: total

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.

Upgrade path

2 packages: 1 fixed.

PackageAffectedFixed inStatus
crates.io deepseek-tui(crates.io) < 0.8.26 0.8.26 Fixed
Hmbown CodeWhale = < 0.8.26 No fix listed Versions listed

Affected products

ProductAffected versionsFixed in
Hmbown CodeWhale = < 0.8.26 No fix listed
crates.io deepseek-tui(crates.io) < 0.8.26 0.8.26

References