CVE-2026-14898 PUBLISHED

Assigner: OAI
Reserved: 06.07.2026 Published: 06.07.2026 Updated: 07.07.2026

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.

Product Status

Vendor OpenAI
Product Codex desktop app for macOS
Versions
  • affected from 0 to 26.527.31326 (excl.)

Affected Configurations

Codex desktop app on macOS with remote Markdown image rendering enabled. Exploitation requires attacker-controlled or untrusted content to be processed by Codex and induce a response containing a remote image URL with sensitive data embedded in the URL.

Workarounds

If an upgrade is not possible, avoid processing untrusted content and connected-tool data in affected versions.

Solutions

Upgrade to 26.527.31326 or later. The product fix disables loading remote images from Markdown.

Credits

  • wuzzi23 (original report)
  • Itay Ravia of Cato Networks (independent report)

References

Problem Types

  • Exposure of Sensitive Information to an Unauthorized Actor