CVE-2026-45311

CRITICAL

CodeWhale: run_tests Tool Enables RCE via Malicious Repository Without Approval

Title source: cna
STIX 2.1

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.

References (1)

Core 1
Core References

Scores

CVSS v3 9.6
EPSS 0.0037
EPSS Percentile 29.1%
Attack Vector NETWORK
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

Details

CWE
CWE-94
Status published
Products (4)
crates.io/deepseek-tui 0.3.0 - 0.8.23crates.io
crates.io/deepseek-tui-cli 0.3.0 - 0.8.23crates.io
Hmbown/CodeWhale >= 0.3.0, < 0.8.23
npm/deepseek-tui 0.3.0 - 0.8.23npm
Published May 28, 2026
Tracked Since May 28, 2026