CVE-2026-45311 PUBLISHED

CodeWhale: run_tests Tool Enables RCE via Malicious Repository Without Approval

Assigner: GitHub_M
Reserved: 11.05.2026 Published: 28.05.2026 Updated: 28.05.2026

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.

Metrics

CVSS Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
CVSS Score: 9.6

Product Status

Vendor Hmbown
Product CodeWhale
Versions
  • Version >= 0.3.0, < 0.8.23 is affected

References

Problem Types

  • CWE-94: Improper Control of Generation of Code ('Code Injection') CWE