CVE 9.6 CRITICAL

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

9.6 / 10
CRITICAL
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.

AI Analysis

Insecure defaults in task_create tool enable RCE via prompt injection in project files

Basic Information

ID CVE-2026-45374
Source GitHub_M
Published May 28, 2026 at 17:26
Modified May 28, 2026 at 17:29

Affected Product

Vendor Hmbown
Product CodeWhale
Version < 0.8.26
Affected Versions Hmbown CodeWhale < 0.8.26

CWE Classification

AI Assessment

AI Score 9.6 / 10
AI Severity Critical
Vendor Hmbown
Product CodeWhale
Version < 0.8.26

References

💭 Join the Security Discussion

🔒 Your email address will not be published. Required fields are marked *

⚠️ Please be respectful and constructive in your comments. Security discussions should remain professional.