CVE-2026-45311
Gravedad CVSS v3.1:
CRÍTICA
Tipo:
CWE-94
Control incorrecto de generación de código (Inyección de código)
Fecha de publicación:
28/05/2026
Última modificación:
01/06/2026
Descripción
*** Pendiente de traducción *** 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.
Impacto
Puntuación base 3.x
9.60
Gravedad 3.x
CRÍTICA