CVE-2026-45311

The record

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.

Affected packages

Related vulnerabilities

• GHSA-wx44-2q6h-j6p8 DeepSeek TUI: run_tests Tool Enables RCE via Malicious Repository Without Approval Same vulnerability
• CVE-2026-45310 CodeWhale is a DeepSeek + MiMo coding agent in terminal. Also affects deepseek-tui
• CVE-2026-45374 CodeWhale is a DeepSeek + MiMo coding agent in terminal. Also affects deepseek-tui
• CVE-2026-45373 CodeWhale is a DeepSeek + MiMo coding agent in terminal. Also affects deepseek-tui
• GHSA-72w5-pf8h-xfp4 DeepSeek TUI: task_create Insecure Defaults Enable RCE via Prompt Injection in Project… Also affects deepseek-tui
• GHSA-88gh-2526-gfrr DeepSeek TUI has SSRF‌ IPV6 bypass Also affects deepseek-tui
• GHSA-96ff-gc8g-wpvg DeepSeek TUI has SSRF via HTTP Redirect Bypass in fetch_url Tool Also affects deepseek-tui
• CVE-2026-114125 Storybook is a frontend workshop for building user interface components and pages in… CWE-94