CVEvulnerability
CVE-2026-45311
9.6 CRITICAL
Official page ↗
- Status
- Deferred
- Published
- 2026-05-28
- Last modified
- 2026-10-26
- Assigner
- [email protected]
- CVSS 3.1 ([email protected])
- 9.6 CRITICAL — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
- Weaknesses
- CWE-94
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.
Related
Weakness · CWE (1)
- CWE-94 Improper Control of Generation of Code weakness