cve.bz

CVE-2026-45311

9.6 criticalEPSS 0.5%

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 3.1
9.6CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
EPSS
0.5% chance of exploitation in the next 30 days; higher than 42% of CVEs (scores of 2026-10-25)
CWE
CWE-94
Published
Modified
Record from
the NVD, synced

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-wx44-2q6h-j6p8crates.iodeepseek-tui>=0.3.0 <0.8.230.8.23
GHSA-wx44-2q6h-j6p8crates.iodeepseek-tui-cli>=0.3.0 <0.8.230.8.23
GHSA-wx44-2q6h-j6p8npmdeepseek-tui>=0.3.0 <0.8.230.8.23

References

Check your stackJSON