CVE-2026-19591

State
Published
Severity
8.8 High
Published
Sep 1, 2026
Updated
Sep 2, 2026
Reserved
Aug 12, 2026

Read the record on cve.org

Description

OpenAI Codex CLI for Windows, macOS, and Linux and Codex Desktop for Windows and macOS misclassified certain PowerShell commands as safe because their command-safety parser interpreted PowerShell's stop-parsing token (--%) differently than PowerShell itself. If a user opens an attacker-prepared repository and Codex follows its instructions, Codex can run a file-writing Git command without requesting user approval. On macOS and Linux, exploitation additionally requires separately installed PowerShell Core (pwsh) to be invoked. If filesystem protections permit the write, the command can modify Codex's configuration. If Codex later loads the modified configuration, it can launch an attacker-controlled MCP server and execute code with the user's privileges, allowing it to read, change, or delete files accessible to that account. The approval bypass does not disable filesystem sandboxing; the default filesystem sandbox on macOS and Linux can prevent writes outside permitted locations.

Scores

CVSSScoreVectorSource
3.18.8 HighCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HCISA-ADP

Weaknesses

  • CWE-150 Improper Neutralization of Escape, Meta, or Control Sequences

Affected Products

ProductVersions
Codex CLIOpenAI
  • 0.72.0 through 0.130.0Affected
  • 0.131.0Not affected
Codex DesktopOpenAI
  • 260202.0859 through 26.513.31313Affected
  • 26.519.22136Not affected
Codex DesktopOpenAI
  • 26.304.38 through 26.513.40821Affected
  • 26.519.21041Not affected
Codex Desktop (Microsoft Store package)OpenAI
  • 26.304.38.0 through 26.513.4821.0Affected
  • 26.519.2081.0Not affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.