CVE-2026-75858

The record

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 packages

Related vulnerabilities

• CVE-2026-114125 Storybook is a frontend workshop for building user interface components and pages in… CWE-94
• CVE-2026-113776 virtualenv is a tool for creating isolated virtual python environments. CWE-94
• CVE-2026-112100 A vulnerability was determined in DeepPavlov up to 1.7.0. CWE-94
• CVE-2026-112095 A flaw has been found in SourceCodester Inventory System 1.0. CWE-94
• CVE-2026-112042 A security flaw has been discovered in diem-project diem up to… CWE-94
• CVE-2026-112038 A vulnerability has been found in diem-project diem up to… CWE-94
• CVE-2026-111991 A security vulnerability has been detected in WongKinYiu yolov9 0.1. CWE-94
• CVE-2026-111986 A vulnerability was determined in AUTOMATIC1111 stable-diffusion-webui up to 1.10.1. CWE-94