Code execution via PowerShell stop-parsing interpretation mismatch
Published Sep 1, 2026 · Updated Sep 2, 2026
Command-safety bypass in OpenAI Codex CLI 0.72.0 through 0.130.0 and Codex Desktop allows remote attackers to execute code. The AST-backed command flattener treats PowerShell's --% stop-parsing form as an argv shape it can safely model, while PowerShell preserves the remaining native-command text. Exploitation requires a user to open the repository and Codex to follow its instructions; successful configuration writes can later launch an attacker-controlled MCP server with the user's file access.
Summary
What happened
Command-safety bypass in OpenAI Codex CLI 0.72.0 through 0.130.0 and Codex Desktop allows remote attackers to execute code. The AST-backed command flattener treats PowerShell's --% stop-parsing form as an argv shape it can safely model, while PowerShell preserves the remaining native-command text. Exploitation requires a user to open the repository and Codex to follow its instructions; successful configuration writes can later launch an attacker-controlled MCP server with the user's file access.
The record
- CVE
- CVE-2026-19591
- Published
- Sep 1, 2026
- Updated
- Sep 2, 2026
- Vendor
- OpenAI
- Product
- Codex Desktop
- Classifications
- CWE-150, T1204, T1059.001
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 1, 2026CVE publishedPublication date reported by the CVE source.
- Sep 2, 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=260202.0859 <=26.513.31313
- Affected versionversion=26.304.38.0 <=26.513.4821.0
- Affected versionversion=26.304.38 <=26.513.40821
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
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
No public exploit references are available in this record.
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