SecurityFan score 20 · Tier C
Researchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak Toolkit
The Hacker News · By info@thehackernews.com (The Hacker News) ·

Cybersecurity researchers have disclosed details of an OpenAI Codex jailbreak bundle that's designed to modify an artificial intelligence (AI) agent's trusted instructions to insert advertisements for a third-party AI gateway. The phenomenon has been codenamed prompt adware by…
The Brief
- Researchers disclosed an OpenAI Codex jailbreak bundle that modifies an AI agent's trusted instructions to insert advertisements for a third-party AI gateway.
- The technique has been codenamed prompt adware.
Why it matters
Untrusted jailbreak tools can silently alter the instructions an AI coding agent treats as trusted, changing its behaviour and injecting third-party content without the developer's knowledge.
Who’s affected
- Developers using OpenAI Codex
- Anyone installing Codex jailbreak tools
What to do
- Avoid installing unverified Codex jailbreak bundles
- #codex
- #prompt-adware
- #ai-agents
- #malware
- #supply-chain


