CVE-2026-45311

Published: Mag 28, 2026 Last Modified: Mag 28, 2026
ExploitDB:
Other exploit source:
Google Dorks:
CRITICAL 9,6
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: none
User Interaction: required
Scope: changed
Confidentiality: high
Integrity: high
Availability: high

Description

AI Translation Available

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.

94

Improper Control of Generation of Code ('Code Injection')

Draft
Abstraction: Base Structure: Simple
Common Consequences
Security Scopes Affected:
Access Control Integrity Confidentiality Availability Non-Repudiation
Potential Impacts:
Bypass Protection Mechanism Gain Privileges Or Assume Identity Execute Unauthorized Code Or Commands Hide Activities
Applicable Platforms
Languages: Interpreted
Technologies: AI/ML
Likelihood of Exploit: Medium
View CWE Details
https://github.com/Hmbown/CodeWhale/security/advisories/GHS…
https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-wx44-2q6h-j6p8