CVE-2026-75858

published 18 Aug 2026 · updated 18 Aug 2026

CodeWhale rlm_eval before 0.8.64 Remote Code Execution

7.8HighCVSS 7.8EPSS 0%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. Fixed in 0.8.41 and 0.8.64.

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.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
Hmbown>=0.8.33 <0.8.41, >=0.8.41 <0.8.640.8.41, 0.8.64

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-75858 severity on Zeptric[![CVE-2026-75858](https://zeptric.io/badge/cve/CVE-2026-75858.svg)](https://zeptric.io/cve/CVE-2026-75858)