CVE-2026-45311
CVE-2026-45311 · CodeWhale: run_tests Tool Enables RCE via Malicious Repository Without Approval
This page contains facts from public vulnerability sources. Check the original advisory before updating.
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.
CVSS 9.6 · Critical · EPSS 0.6% · Fix available
- Published
- Updated
Stack: node
Affected products and versions
codewhale
- Versions
- >= 0.3.0, < 0.8.23: Affected
No fix published
deepseek-tui crates.io
- Affected ranges
- SEMVER: ≥ 0.3.0, < 0.8.23
Update to 0.8.23
deepseek-tui-cli crates.io
- Affected ranges
- SEMVER: ≥ 0.3.0, < 0.8.23
Update to 0.8.23
deepseek-tui npm
- Affected ranges
- SEMVER: ≥ 0.3.0, < 0.8.23
Update to 0.8.23