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.

No CVSS v4.0

Attack Vector Network

Attack Complexity Low

Privileges Required None

Scope Changed

Confidentiality Impact High

Integrity Impact High

Availability Impact High

User Interaction Required

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

No EPSS score available.

Key SSVC decision points have not yet been added.

Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).

Vendor Product Default status Versions
Hmbown CodeWhale affected
Version Status Constraints
< 0.8.26 affected —

No data.

No data.

OpenCVE Enrichment is a feature of OpenCVE that uses AI to automatically link vendors and products to CVEs. Learn more on GitHub.

No data.

Project Subscriptions

No data.

Advisories
Source ID Title
Github GHSA Github GHSA GHSA-72w5-pf8h-xfp4 DeepSeek TUI: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files
Fixes

Solution

No solution given by the vendor.

Workaround

No workaround given by the vendor.

References
Link Providers
https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4 cve-icon cve-icon
https://github.com/Hmbown/DeepSeek-TUI/releases/tag/v0.8.26 cve-icon cve-icon
History

Thu, 28 May 2026 18:00:00 +0000

Type Values Removed Values Added
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.
Title CodeWhale: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files
Weaknesses CWE-94
References
Metrics cvssV3_1

{'score': 9.6, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H'}

Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-05-28T17:29:11.005Z

Reserved: 2026-05-12T00:51:29.086Z

Link: CVE-2026-45374

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Deferred

Published: 2026-05-28T18:16:35.843

Modified: 2026-05-28T18:40:37.990

Link: CVE-2026-45374

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-05-28T19:30:16Z

Weaknesses