CVE-2026-45311

CodeWhale: run_tests Tool Enables RCE via Malicious Repository Without Approval

State
Published
Severity
9.6 Critical
Published
May 28, 2026
Updated
Jun 1, 2026
Reserved
May 11, 2026

Read the record on cve.org

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.

Scores

CVSSScoreVectorSource
3.19.6 CriticalCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:HGitHub_M

Weaknesses

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

Affected Products

ProductVersions
CodeWhaleHmbown
  • >= 0.3.0, < 0.8.23Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.