CVE-2026-75858
Published:August 18, 2026
Updated:September 23, 2026
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
https://github.com/Hmbown/CodeWhale.git (GITHUB):
Affected version(s) >=v0.8.33 <v0.8.64Fix Suggestion:
Update to version v0.8.64deepseek-tui (NPM):
Affected version(s) >=0.8.33 <0.8.41Fix Suggestion:
Update to version 0.8.41codewhale (NPM):
Affected version(s) >=0.8.41 <0.8.64Fix Suggestion:
Update to version 0.8.64codewhale-tui (RUST):
Affected version(s) >=0.8.41 <0.8.64Fix Suggestion:
Update to version 0.8.64Related Resources (6)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.5
Attack Vector
LOCAL
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
PASSIVE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
HIGH
Vulnerable System Availability
HIGH
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
7.8
Attack Vector
LOCAL
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
REQUIRED
Scope
UNCHANGED
Confidentiality
HIGH
Integrity
HIGH
Availability
HIGH
Weakness Type (CWE)
EPSS
Base Score:
0.27