CyberRota Analysis
AI-GeneratedThe OpenAI Codex desktop app for macOS is vulnerable due to its automatic fetching of remote images from Markdown-rendered model responses, which can be manipulated through indirect prompt injection. This flaw allows an attacker to exfiltrate sensitive information, such as API keys and source code, to their server without user interaction. Organizations using the Codex app should prioritize addressing this vulnerability to protect against potential data leaks.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD 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.