CodeWhale rlm_eval before 0.8.64 Remote Code Execution
Hmbown CodeWhale
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| deepseek-tui crates.io |
| No fix yet |
| deepseek-tui npm |
|
|
| codewhale-tui crates.io |
|
Hmbown CodeWhale
| Product | Affected | Fixed in |
|---|---|---|
| deepseek-tui crates.io |
| No fix yet |
| deepseek-tui npm |
|
|
| codewhale-tui crates.io |
|
|
| codewhale npm |
|
|
CodeWhale (packages codewhale / codewhale-tui) versions >= 0.8.41 and < 0.8.64 contain a remote code execution vulnerability in the rlm_eval tool. The tool's approval_requirement() returns ApprovalRequirement::Auto, which the engine treats as 'never prompt,' causing arbitrary model-supplied Python code to run in a python3 interpreter without consulting the user's configured --approval-policy and without any approval prompt or audit step. An attacker can induce the agent to execute arbitrary code via prompt injection in untrusted content the agent reads (a web page, fetched URL, repository file, or MCP tool result); the companion rlm_open tool can stage such content. Code runs on the user's machine at the user's privilege level. Fixed in 0.8.64.
From the CVE record · VulnCheck
The rlm_eval tool can run model-supplied Python code on a user's machine without an approval prompt, even when the user's approval policy requires one. An attacker can trigger this through prompt injection in untrusted content the agent reads, such as a web page, repository file, or tool result. The code runs with the user's privileges.
Check installations of npm codewhale and crates.io codewhale-tui from 0.8.41 up to but not including 0.8.64, npm deepseek-tui from 0.8.33 up to but not including 0.8.41, and crates.io deepseek-tui from 0.8.33 through 0.8.41.