HighVulnerabilityLLM-specific

CVE-2026-19591: OpenAI Codex CLI and Desktop approval bypass via PowerShell

Source: NVD(opens in a new tab)
Identifier: CVE-2026-19591
Published: September 1, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.6%

Summary

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 read the stop-parsing token (--%) differently than PowerShell does. If a user opens an attacker-prepared repository and Codex follows its instructions, Codex can run a file-writing Git command without requesting approval. If filesystem protections permit the write, the attacker can modify Codex's configuration so that a later load launches an attacker-controlled MCP server, executing code with the user's privileges.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

EPSS: 0.6%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.
Disclosure date: September 1, 2026

Weaknesses and techniques

Weakness (CWE): CWE-150
AI threat technique (MITRE ATLAS): AML.T0051

Affected

Vendors: OpenAI

Classification

Attack type: Prompt injection,
Other
Attack sophistication: Moderate
AI component targeted: Agent
Impact: Integrity,
Confidentiality,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-19591

First tracked: September 1, 2026 at 08:08 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Topics

Model Context Protocol

Summary

Mitigation

Topics

Related items