CVE-2026-45374: Hmbown CodeWhale RCE via insecure sub-agent defaults

CVE-2026-45374 · Severity: critical · CVSS 9.6 · Published 2026-05-28

DeepSeek TUI is a terminal-based interface for interacting with AI models. A vulnerability exists where the tool's sub-agents are granted unrestricted shell access by default when a user approves a seemingly benign task. If a developer opens a malicious project repository, an attacker can use hidden instructions to trick the AI into executing harmful commands on the user's computer without further approval, potentially leading to full system compromise.

Technologies: deepseek-tui (crates.io), Hmbown CodeWhale. Vendors: crates.io, Hmbown.

Quick answers

Is CVE-2026-45374 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-45374 being exploited in the wild.
How severe is CVE-2026-45374?
Critical severity, with a CVSS score of 9.6, published 28 May 2026.
Which products and versions are affected?
deepseek-tui (crates.io) < 0.8.26, SEMVER:introduced=0,fixed=0.8.26; Hmbown CodeWhale < 0.8.26.
Is there a fix for CVE-2026-45374?
Yes. deepseek-tui (crates.io): upgrade to 0.8.26 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-45374 attacked?
It is attacked over the network, in a network appliance.
Am I affected by CVE-2026-45374?
Check whether you run deepseek-tui (crates.io) or Hmbown CodeWhale at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

  • deepseek-tui (crates.io): upgrade to 0.8.26 or later
    cargo update -p deepseek-tui

Technical details

The vulnerability stems from insecure defaults in the `task_create` tool within `deepseek-tui`. Specifically, `allow_shell` and `auto_approve` both default to `true` for spawned sub-agents. An attacker can craft a malicious repository containing prompt injection instructions (e.g., in an `AGENTS.md` file). When a user approves a high-level task creation, the sub-agent reads these instructions and executes arbitrary shell commands via the inherited permissions without triggering additional user approval prompts. This bypasses the intended security boundary of the approval system. The issue is fixed in version 0.8.26 by changing these defaults to `false`.

Affected products

  • Hmbown/CodeWhale deepseek-tui < 0.8.26

Identifiers

  • CVE-2026-45374
  • GHSA-72w5-pf8h-xfp4

Timeline

  • 2026-05-10: disclosed
  • 2026-05-14: advisory: GitHub Advisory published
  • 2026-05-28: other: NVD published

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.