CVE-2026-75858: Improper Control of Generation of Code ('Code Injection') in Hmbown CodeWhale
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.
AI Analysis
Technical Summary
CodeWhale (packages codewhale / codewhale-tui) versions >=0.8.41 and <0.8.64 have a remote code execution vulnerability in the rlm_eval tool. The approval_requirement() function returns ApprovalRequirement::Auto, which the engine treats as 'never prompt,' causing arbitrary Python code from model-supplied input to run in a python3 interpreter without consulting the user's configured approval policy or prompting for approval. An attacker can exploit this via prompt injection in untrusted content the agent reads, including web pages, fetched URLs, repository files, or MCP tool results. The companion rlm_open tool can stage such content. Code executes on the user's machine with the user's privilege level. The issue is fixed in version 0.8.64.
Potential Impact
An attacker can cause arbitrary Python code execution on the user's machine at the user's privilege level without any approval prompt or audit step. This can lead to full compromise of the affected system depending on the user's privileges. The vulnerability affects local users who run the vulnerable versions and interact with untrusted content processed by the agent.
Mitigation Recommendations
Upgrade CodeWhale to version 0.8.64 or later, where this vulnerability is fixed. Until then, avoid processing untrusted content with the vulnerable versions. No official patch or temporary fix is indicated beyond upgrading to the fixed version.
CVE-2026-75858: Improper Control of Generation of Code ('Code Injection') in Hmbown CodeWhale
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.
CVSS v4.0
Score 8.5high
Affected software
pkg:github/hmbown/CodeWhaleRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CodeWhale (packages codewhale / codewhale-tui) versions >=0.8.41 and <0.8.64 have a remote code execution vulnerability in the rlm_eval tool. The approval_requirement() function returns ApprovalRequirement::Auto, which the engine treats as 'never prompt,' causing arbitrary Python code from model-supplied input to run in a python3 interpreter without consulting the user's configured approval policy or prompting for approval. An attacker can exploit this via prompt injection in untrusted content the agent reads, including web pages, fetched URLs, repository files, or MCP tool results. The companion rlm_open tool can stage such content. Code executes on the user's machine with the user's privilege level. The issue is fixed in version 0.8.64.
Potential Impact
An attacker can cause arbitrary Python code execution on the user's machine at the user's privilege level without any approval prompt or audit step. This can lead to full compromise of the affected system depending on the user's privileges. The vulnerability affects local users who run the vulnerable versions and interact with untrusted content processed by the agent.
Mitigation Recommendations
Upgrade CodeWhale to version 0.8.64 or later, where this vulnerability is fixed. Until then, avoid processing untrusted content with the vulnerable versions. No official patch or temporary fix is indicated beyond upgrading to the fixed version.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-08-18T11:03:08.682Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a847b9ec6e8be03326654c3
Added to database: 08/18/2026, 15:34:54 UTC
Last enriched: 08/18/2026, 15:50:46 UTC
Last updated: 08/19/2026, 03:58:07 UTC
Views: 4
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.