CVE-2026-83816
Received Received - Intake

CodeWhale Agent Command Injection Vulnerability

Vulnerability report for CVE-2026-83816, including description, CVSS score, EPSS score, affected products, exploitability, helpful resources, and attack-flow context.

Publication date: 2026-11-16

Last updated on: 2026-11-16

Assigner: GitHub, Inc.

Description

CodeWhale is a DeepSeek and MiMo coding agent for the terminal. Prior to 0.9.0, the ExecShellTool::approval_requirement_for path used is_parallel_readonly_command to downgrade commands to automatic approval based on a flag-stripped command allowlist. The allowlist treated fd, rg, and git grep as read-only even when fd -x or fd --exec, rg --pre, or git grep --open-files-in-pager selected an external program. registered_tool_approval_required returned without displaying a prompt for that automatic classification, and the later command-safety check also treated the base utilities as safe. Attacker-controlled content that influenced an agent tool call could therefore cause arbitrary program execution on the developer host without the approval promised by the default interactive profile, resulting in unauthorized access, modification, or disruption. This issue is fixed in version 0.9.0.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-11-16
Last Modified
2026-11-16
Generated
2026-11-16
AI Q&A
2026-11-16
EPSS Evaluated
N/A
NVD
EUVD

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
codewhale codewhale 0.9.0

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-863 The product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check.
CWE-78 The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability in CodeWhale versions before 0.9.0 allows arbitrary code execution on a developer's system without user approval. The issue occurs because the system incorrectly classifies commands like fd, rg, and git grep as safe even when they include exec flags (e.g., fd -x). Attackers can exploit this by tricking the AI model into using these commands, bypassing security prompts and executing malicious code.

Detection Guidance

Check CodeWhale version with 'codewhale --version' or inspect package.json for codewhale-tui. Look for suspicious shell commands using fd, rg, or git grep with exec flags like -x, --pre, or --open-files-in-pager in logs or automation scripts.

Impact Analysis

If exploited, this vulnerability could allow unauthorized access to your system, modification or deletion of files, or disruption of operations. Attackers could run arbitrary programs without your knowledge, potentially stealing sensitive data or installing malware.

Compliance Impact

This vulnerability could lead to unauthorized data access or modification, violating GDPR's data protection requirements or HIPAA's safeguards for protected health information. Organizations using affected versions may face compliance breaches, legal penalties, and reputational damage.

Mitigation Strategies

Upgrade CodeWhale to version 0.9.0 or later immediately. Review and remove exec-capable tools from parallel-readonly allowlists. Audit automation scripts for unauthorized shell commands and disable automations using default auto-approve settings.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-83816. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart

Security Radar

News mentioning this vulnerability
Loading related security news...