dbcve.org
Code InjectionWeakness · CWE-94

CVE-2026-45374

CRITICAL · 9.6 CVSS v3.1 Published 2026-05-28
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
100/100
Remediation priority · Urgent
Remotely reachable No privileges

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
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.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

In CodeWhale prior to 0.8.26, the task_create tool spawns durable sub-agents that inherit two insecure defaults: allow_shell defaults to true and auto_approve defaults to true. When users approve a task_create call (which requires ApprovalRequirement::Required), the spawned sub-agent silently receives unrestricted, unapproved shell access, bypassing the approval mechanism.

MitigationUpgrade CodeWhale to version 0.8.26 or later where allow_shell and auto_approve default to false.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
Required
Scope
Changed
Confidentiality
High
Integrity
High
Availability
High

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

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Check CodeWhale version
    Run 'codewhale --version' or check the installed package version to determine if it is prior to 0.8.26
    Affected if Version is below 0.8.26
  2. Identify task_create usage
    Review logs, audit trails, or configuration files to see if the task_create tool has been invoked to spawn sub-agents
    Affected if task_create has been used to spawn durable sub-agents
  3. Inspect allow_shell default setting
    Examine CodeWhale configuration files or runtime settings for the allow_shell parameter on sub-agents spawned via task_create; check if it defaults to true
    Affected if allow_shell is set to true for sub-agents without explicit user configuration
  4. Inspect auto_approve default setting
    Examine CodeWhale configuration files or runtime settings for the auto_approve parameter on sub-agents spawned via task_create; check if it defaults to true
    Affected if auto_approve is set to true for sub-agents without explicit user configuration
  5. Review approval bypass evidence
    Compare the approval requests: check if a task_create approval was granted but subsequent shell commands executed by the sub-agent were not subject to additional approval prompts
    Affected if Shell commands executed by sub-agents without requiring separate approval after initial task_create approval

A user is affected if running CodeWhale version below 0.8.26 and has used task_create to spawn sub-agents where allow_shell and auto_approve are both true, allowing shell access without proper approval checks.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Upgrade CodeWhale to version 0.8.26 or later where allow_shell and auto_approve default to false.

Recommended fix Moderate confidence

0.8.26

  1. Check current CodeWhale version (e.g., codewhale --version or see installation method used)
  2. Upgrade to CodeWhale version 0.8.26 or later using your package manager or installation method (e.g., pip install --upgrade codewhale, brew upgrade, or download from releases)
  3. Verify the upgrade was successful by checking the version

Generated from the published advisory — verify against the referenced sources before acting.

Have this fixed Scoped from the published advisory
  • Consultation2.0 h
  • Implementation2.0 h
  • Testing4.0 h
  • Review / QA1.0 h
9.0 hours of engineering $1,540
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $2,464.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-45374 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-45374 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data