Prompt adware found hidden in OpenAI Codex jailbreak toolkit
AI SECURITYOpenAI Codexredteam/daily · 1 source
- Severity
- Medium
- Sources
- 1
What happened
Check Point Research disclosed a jailbreak bundle called Haiou, aimed at OpenAI Codex, which it has named prompt adware. The bundle modifies the AI agent's trusted instructions and its configuration to insert advertisements for a third-party AI gateway.
For IT people · Written by AI from 1 source · Wrong?
What to do
- Avoid installing jailbreak bundles for OpenAI Codex, as this one was found to modify the agent's trusted instructions.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
The Hacker News
Who and what is in it
Companies
Products