The OpenAI Codex desktop app for macOS rendered remote images from Markdown in model responses. An attacker who could place an indirect prompt injection in content processed by Codex, such as a connected-tool result or another untrusted source, could induce the model to construct a remote image URL containing sensitive data. The app automatically fetched that URL when rendering the response, sending the embedded data to an attacker-controlled server without a separate user click. Successful exploitation could exfiltrate secrets and other information accessible in the Codex session, including API keys, source code, and data returned by connected tools. No direct integrity or availability impact was demonstrated, and there is no known exploitation in the wild.
Advisories
No advisories yet.
Fixes
Solution
Upgrade to 26.527.31326 or later. The product fix disables loading remote images from Markdown.
Workaround
If an upgrade is not possible, avoid processing untrusted content and connected-tool data in affected versions.
References
| Link | Providers |
|---|---|
| https://openai.com/codex/ |
|
History
Tue, 07 Jul 2026 05:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Title | Exfiltration via Remote Image Loading in OpenAI Codex Desktop App |
Mon, 06 Jul 2026 23:15:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Openai
Openai codex Desktop App For Macos |
|
| Vendors & Products |
Openai
Openai codex Desktop App For Macos |
Mon, 06 Jul 2026 19:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Description | The OpenAI Codex desktop app for macOS rendered remote images from Markdown in model responses. An attacker who could place an indirect prompt injection in content processed by Codex, such as a connected-tool result or another untrusted source, could induce the model to construct a remote image URL containing sensitive data. The app automatically fetched that URL when rendering the response, sending the embedded data to an attacker-controlled server without a separate user click. Successful exploitation could exfiltrate secrets and other information accessible in the Codex session, including API keys, source code, and data returned by connected tools. No direct integrity or availability impact was demonstrated, and there is no known exploitation in the wild. | |
| Weaknesses | CWE-200 | |
| References |
|
Projects
Sign in to view the affected projects.
Status: PUBLISHED
Assigner: OAI
Published:
Updated: 2026-07-06T19:41:36.632Z
Reserved: 2026-07-06T19:35:48.882Z
Link: CVE-2026-14898
No data.
No data.
No data.
OpenCVE Enrichment
Updated: 2026-07-07T05:30:04Z
Weaknesses