Vulnerability in Openai Codex Cli
CVE-2026-19591
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 8.8 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS: 0.003 (21.8th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 22nd percentile — 21.8% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.003 · newest: 0.003 · change: 0.000
Affected products
Weakness classification (CWE)
References
Frequently asked questions
- What is CVE-2026-19591?
- CVE-2026-19591 is a high-severity vulnerability in Openai Codex Cli, classified under CWE-150. CVSS score: 8.8/10. Published 2026-09-01.
- How severe is CVE-2026-19591?
- High severity. CVSS v3 base score is 8.8 out of 10.