Vulnerability · Published May 28, 2026 · Assigned by GitHub_M
CVE-2026-45311CodeWhale: run_tests Tool Enables RCE via Malicious Repository Without Approval
Critical 9.6
In plain English
A critical-severity code injection in CodeWhale from Hmbown. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 47% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official description
CodeWhale is a DeepSeek + MiMo coding agent in terminal. From 0.3.0 to 0.8.23, the run_tests tool executes cargo test in the workspace with ApprovalRequirement::Auto, meaning it runs without any user approval prompt. cargo test compiles and executes arbitrary code: test binaries, build.rs build scripts, and proc macros. While auto-approving test execution is a deliberate design choice, it creates an inconsistency in the security boundary. However, in a malicious repository, test code can execute arbitrary shell commands, exfiltrate credentials, or establish persistence with zero approval. The attack is amplified by AGENTS.md (auto-loaded into the system prompt), which can instruct the model to run tests proactively at session start. This vulnerability is fixed in 0.8.23.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| npm | deepseek-tui | 0.8.23 | GHSA-wx44-2q6h-j6p8 |
Affected products (as reported)
Weakness: CWE-94 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
References
- https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-wx44-2q6h-j6p8 x_refsource_CONFIRM