# OpenAI vulnerabilities Source: https://junglewise.ai/threats/vendors/openai Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats Updated: 13 November 2026, 03:07 UTC. Rebuilt every hour. Data: https://junglewise.ai/threats/vendors/openai.json License: CC BY 4.0 with a link back Junglewise Threat Intelligence has tracked 8 vulnerabilities in OpenAI: 0 in the last 7 days and 5 in the last 90 days, 2 of them critical and 0 exploited in the wild. The most recent, CVE-2026-110930, was published on 5 November 2026. 1 vulnerability in the last four weeks, up from none in the four before. 2 technologies have a page of their own. ## Counts - Last 7 days: 0 - Last 30 days: 1 - Last 90 days: 5 - All time: 8 (2 critical, 0 exploited in the wild) ## About OpenAI An artificial intelligence research and deployment company. ## Latest OpenAI vulnerabilities - [CVE-2026-110930: Codex Desktop for Windows code execution via unquoted path in file explorer](https://junglewise.ai/threats/cve-2026-110930-codex-desktop-for-windows-does-not-correctly-check-quotation) (info, published 5 Nov 2026) - [CVE-2026-19593: OpenAI Codex Desktop arbitrary code execution via Git config](https://junglewise.ai/threats/cve-2026-19593-openai-codex-desktop-arbitrary-code-execution-via-git-config) (critical, CVSS 9.8, published 1 Sep 2026) - [CVE-2026-19592: OpenAI Codex CLI and Desktop Git fsmonitor code execution](https://junglewise.ai/threats/cve-2026-19592-openai-codex-cli-and-desktop-git-fsmonitor-code-execution) (high, CVSS 7.3, published 1 Sep 2026) - [CVE-2026-19591: OpenAI Codex CLI and Desktop PowerShell command-safety bypass](https://junglewise.ai/threats/cve-2026-19591-openai-codex-cli-and-desktop-powershell-command-safety-bypass) (high, CVSS 8.8, published 1 Sep 2026) - [CVE-2026-19590: OpenAI Codex Desktop arbitrary code execution via Git hooks](https://junglewise.ai/threats/cve-2026-19590-openai-codex-desktop-arbitrary-code-execution-via-git-hooks) (high, CVSS 7.3, published 1 Sep 2026) - [CVE-2026-11326: OpenAI Atlas privileged API exposure via XSS in forum.openai.com](https://junglewise.ai/threats/cve-2026-11326-openai-atlas-privileged-api-exposure-via-xss-in-forum-openai-com) (info, CVSS 8.8, published 5 Jun 2026) - [CVE-2025-61260: OpenAI Codex CLI code execution via project-local configuration](https://junglewise.ai/threats/cve-2025-61260-openai-codex-cli-code-execution-via-project-local-configuration) (critical, CVSS 9.8, published 14 Apr 2026) - [CVE-2025-59532: OpenAI Codex sandbox bypass in path configuration](https://junglewise.ai/threats/cve-2025-59532-openai-codex-sandbox-bypass-in-path-configuration) (medium, CVSS 4, published 19 Sep 2025) ## Most severe OpenAI vulnerabilities - [CVE-2025-61260: OpenAI Codex CLI code execution via project-local configuration](https://junglewise.ai/threats/cve-2025-61260-openai-codex-cli-code-execution-via-project-local-configuration) (critical, CVSS 9.8, published 14 Apr 2026) - [CVE-2026-19593: OpenAI Codex Desktop arbitrary code execution via Git config](https://junglewise.ai/threats/cve-2026-19593-openai-codex-desktop-arbitrary-code-execution-via-git-config) (critical, CVSS 9.8, published 1 Sep 2026) - [CVE-2026-19591: OpenAI Codex CLI and Desktop PowerShell command-safety bypass](https://junglewise.ai/threats/cve-2026-19591-openai-codex-cli-and-desktop-powershell-command-safety-bypass) (high, CVSS 8.8, published 1 Sep 2026) - [CVE-2026-19592: OpenAI Codex CLI and Desktop Git fsmonitor code execution](https://junglewise.ai/threats/cve-2026-19592-openai-codex-cli-and-desktop-git-fsmonitor-code-execution) (high, CVSS 7.3, published 1 Sep 2026) - [CVE-2026-19590: OpenAI Codex Desktop arbitrary code execution via Git hooks](https://junglewise.ai/threats/cve-2026-19590-openai-codex-desktop-arbitrary-code-execution-via-git-hooks) (high, CVSS 7.3, published 1 Sep 2026) - [CVE-2025-59532: OpenAI Codex sandbox bypass in path configuration](https://junglewise.ai/threats/cve-2025-59532-openai-codex-sandbox-bypass-in-path-configuration) (medium, CVSS 4, published 19 Sep 2025) - [CVE-2026-11326: OpenAI Atlas privileged API exposure via XSS in forum.openai.com](https://junglewise.ai/threats/cve-2026-11326-openai-atlas-privileged-api-exposure-via-xss-in-forum-openai-com) (info, CVSS 8.8, published 5 Jun 2026) - [CVE-2026-110930: Codex Desktop for Windows code execution via unquoted path in file explorer](https://junglewise.ai/threats/cve-2026-110930-codex-desktop-for-windows-does-not-correctly-check-quotation) (info, published 5 Nov 2026) ## Vulnerabilities per week 1 vulnerability in the last four weeks, up from none in the four before. | Week of | Vulns | Critical | Exploited | | --- | --- | --- | --- | | 17 Aug 2026 | 0 | 0 | 0 | | 24 Aug 2026 | 0 | 0 | 0 | | 31 Aug 2026 | 4 | 1 | 0 | | 7 Sep 2026 | 0 | 0 | 0 | | 14 Sep 2026 | 0 | 0 | 0 | | 21 Sep 2026 | 0 | 0 | 0 | | 28 Sep 2026 | 0 | 0 | 0 | | 5 Oct 2026 | 0 | 0 | 0 | | 12 Oct 2026 | 0 | 0 | 0 | | 19 Oct 2026 | 0 | 0 | 0 | | 26 Oct 2026 | 0 | 0 | 0 | | 2 Nov 2026 | 1 | 0 | 0 | | 9 Nov 2026 | 0 | 0 | 0 | ## OpenAI technologies - [OpenAI Codex Desktop](https://junglewise.ai/threats/technologies/codex-desktop): 5 vulnerabilities - [OpenAI Codex CLI](https://junglewise.ai/threats/technologies/codex-cli): 3 vulnerabilities ## Sources NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories. Rebuilt every hour. Cite as: Junglewise Threat Intelligence, "OpenAI vulnerabilities", https://junglewise.ai/threats/vendors/openai, 13 November 2026.