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
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
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 3.1 | 9.6 Critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H | GitHub_M |
Weaknesses
- CWE-94 Improper Control of Generation of Code ('Code Injection')
Affected Products
| Product | Versions |
|---|---|
CodeWhaleHmbown |
|
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.