Local command execution via unescaped model argument
Published Aug 9, 2026 · Updated Aug 9, 2026
Command injection in Codex MCP Server allows local users to execute OS commands through the ask tool's model argument. The ask handler appends the caller-controlled model value to Codex CLI flags without escaping, joins the arguments into a shell command, and passes it to execAsync. An attacker needs low-privilege local access to invoke the MCP tool; injected commands run with the server process's privileges.
Summary
What happened
Command injection in Codex MCP Server allows local users to execute OS commands through the ask tool's model argument. The ask handler appends the caller-controlled model value to Codex CLI flags without escaping, joins the arguments into a shell command, and passes it to execAsync. An attacker needs low-privilege local access to invoke the MCP tool; injected commands run with the server process's privileges.
The record
- CVE
- CVE-2026-19329
- Published
- Aug 9, 2026
- Updated
- Aug 9, 2026
- Vendor
- andreahaku
- Product
- Codex MCP Server
- Classifications
- CWE-77, CWE-74, T1059
- Attack vector
- local
- Privileges
- authenticated
Timeline
How it unfolded
- Aug 9, 2026CVE publishedPublication date reported by the CVE source.
- Aug 9, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=1ff521cc6cc57cfe56ddef946c644b8534771390
What conditions does exploitation require?
What is affected?
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- ask model command-injection proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo