CVE-2026-19329: Command Injection in andreahaku codex_mcp
A vulnerability was found in andreahaku codex_mcp up to 1ff521cc6cc57cfe56ddef946c644b8534771390. The affected element is an unknown function of the file src/codex-process-simple.ts of the component ask MCP Tool. The manipulation of the argument model results in command injection. The attack requires a local approach. This product does not use versioning. This is why information about affected and unaffected releases are unavailable. The project was informed of the problem early through an issue report but has not responded yet.
AI Analysis
Technical Summary
The vulnerability in andreahaku codex_mcp up to commit 1ff521cc6cc57cfe56ddef946c644b8534771390 involves command injection via manipulation of the 'model' argument in an unknown function within src/codex-process-simple.ts. Exploitation requires local access and low privileges, with no user interaction needed. The product lacks versioning, preventing clear identification of affected versions. The project was notified but has not issued a fix or response. The CVSS 3.1 base score is 5.3, reflecting low severity with impacts on confidentiality, integrity, and availability.
Potential Impact
Successful exploitation could allow an attacker with local access and low privileges to execute arbitrary commands on the affected system, potentially leading to limited confidentiality, integrity, and availability impacts. However, the attack surface is constrained by the requirement for local access and the absence of user interaction.
Mitigation Recommendations
No official fix or patch is currently available as the project has not responded to the issue report. Users should monitor the project for updates or advisories. Until a fix is provided, restricting local access to trusted users and environments is recommended to reduce risk.
CVE-2026-19329: Command Injection in andreahaku codex_mcp
Description
A vulnerability was found in andreahaku codex_mcp up to 1ff521cc6cc57cfe56ddef946c644b8534771390. The affected element is an unknown function of the file src/codex-process-simple.ts of the component ask MCP Tool. The manipulation of the argument model results in command injection. The attack requires a local approach. This product does not use versioning. This is why information about affected and unaffected releases are unavailable. The project was informed of the problem early through an issue report but has not responded yet.
CVSS v4.0
Score 4.8medium
Affected software
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability in andreahaku codex_mcp up to commit 1ff521cc6cc57cfe56ddef946c644b8534771390 involves command injection via manipulation of the 'model' argument in an unknown function within src/codex-process-simple.ts. Exploitation requires local access and low privileges, with no user interaction needed. The product lacks versioning, preventing clear identification of affected versions. The project was notified but has not issued a fix or response. The CVSS 3.1 base score is 5.3, reflecting low severity with impacts on confidentiality, integrity, and availability.
Potential Impact
Successful exploitation could allow an attacker with local access and low privileges to execute arbitrary commands on the affected system, potentially leading to limited confidentiality, integrity, and availability impacts. However, the attack surface is constrained by the requirement for local access and the absence of user interaction.
Mitigation Recommendations
No official fix or patch is currently available as the project has not responded to the issue report. Users should monitor the project for updates or advisories. Until a fix is provided, restricting local access to trusted users and environments is recommended to reduce risk.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-5pgh-4pr5-mhm8
- Osv Schema Version
- 1.4.0
- Aliases
- ["CVE-2026-19329"]
- Database Specific Severity
- LOW
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6a7891cebf8831d539c86489
Added to database: 08/09/2026, 14:42:22 UTC
Last enriched: 08/09/2026, 14:46:45 UTC
Last updated: 09/24/2026, 01:47:41 UTC
Views: 120
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.