What’s Vulnerable › Vulnerabilities

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

• Severity: critical (CVSS 9.6 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.3% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-05-28 · updated 2026-10-26
• Weakness: CWE-94

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.

Affected products

• Hmbown CodeWhale: before 0.8.26

References

• https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4
• https://github.com/Hmbown/DeepSeek-TUI/releases/tag/v0.8.26
• https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4

Get alerted when CVE-2026-45374 or the next vulnerability affects your stack