CVE-2026-45311: Hmbown Codewhale

Critical severity, CVSS 9.6. EPSS: 0.7% chance of exploitation in the next 30 days.

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 products

  • Hmbown Codewhale: from 0.3.0, before 0.8.23 (fixed in 0.8.23)

Published 2026-05-28. Last modified 2026-06-17.