Protected: Is it An Issue? TOCTOU to Prompt Injection in OpenAI’s Codex Cloud Code Review

A security researcher disclosed a time-of-check-to-time-of-use (TOCTOU) vulnerability in OpenAI's Codex cloud code review that could enable prompt injection attacks. The flaw, which affects the AI-powered code review tool, allows an attacker to manipulate the review process by altering code between the time it is checked and the time it is reviewed, potentially leading to malicious code being approved. OpenAI has not yet commented on the issue.