QSearchQSearch

CVE-2026-45311

9.6 CRITICAL

CodeWhale is a DeepSeek + MiMo coding agent in terminal

Published: 2026-05-28 · Last updated: 2026-06-01

Severity and scoring

CVSS
9.6 CRITICAL
Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
CWE
CWE-94

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.

Source: NVD

References

Related CVEs

Same CWE

  • CVE-2026-50223 — Improper Control of Generation of Code ('Code Injection') vulnerability in Apache OFBiz allows a low-privileged authenticated user with C...
  • CVE-2026-45558 — Roxy-WI is a web interface for managing Haproxy, Nginx, Apache and Keepalived servers (9.9 CRITICAL)
  • CVE-2026-46517 — LMDeploy is a toolkit for compressing, deploying, and serving large language models (7.8 HIGH)
  • CVE-2026-46432 — LMDeploy is a toolkit for compressing, deploying, and serving large language models (7.8 HIGH)
  • CVE-2026-47292 — Inclusion of functionality from untrusted control sphere in Visual Studio Code allows an unauthorized attacker to elevate privileges locally (7.8 HIGH)