CVE-2026-75858
Description
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.
How to fix
- codewhale-tui0.8.64 or later
- deepseek-tui0.8.41 or later
- codewhale0.8.64 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| codewhale-tuicrates.io | 0.8.41 ≤ v < 0.8.64 | 0.8.64 |
| deepseek-tuicrates.io | 0.8.33 ≤ v ≤ 0.8.41, 0.8.33 ≤ v < 0.8.41 | 0.8.41 |
| codewhalenpm | 0.8.41 ≤ v < 0.8.64 | 0.8.64 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.