Researchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak Toolkit
Researchers discover 'prompt adware' in OpenAI Codex jailbreak toolkit injecting ads for third-party AI gateways.
Cybersecurity researchers have identified a jailbreak toolkit for OpenAI Codex, dubbed Haiou, that injects advertisements for a third-party AI gateway into agent responses. This 'prompt adware' modifies the AI's trusted instructions to promote a paid gateway service, potentially serving as an acquisition channel. The technique highlights how malicious actors can introduce undesirable behaviors into AI agents through configurations and third-party components, posing a supply chain risk.
AI summary of the linked source. Not reviewed by an editor. How this works
Run OpenAI?
Get an email when a new story names OpenAI, usually within the hour.
Free. Your list stays private and never appears in a subject line. One click stops it. How Vendor Watch worksPrivacy
The lesson from this incident
Full lessonResearchers discovered that a third-party jailbreak toolkit called Haiou secretly injected promotional content into OpenAI Codex agent responses by tampering with the AI's trusted system-level instructions. This 'prompt adware' demonstrates how malicious or unvetted third-party AI components can silently alter agent behavior without the user's knowledge, undermining the integrity of AI-driven workflows. The incident illustrates a growing supply chain risk unique to the AI era: configurations, plugins, and third-party gateways can serve as vectors for manipulating AI outputs. Organizations adopting AI agents must treat every external component—including prompts, toolkits, and middleware—with the same scrutiny applied to traditional software dependencies.
What helps against this
How we list vendors
- Threat intelligence
Attack campaigns reach your sector, suppliers or software before your team hears about them.
- AI application security
Prompt injection, data leaks through AI tools and unapproved AI use get caught.
- Software supply chain security
Malicious and vulnerable open-source packages are caught before they ship.
Indicators of Compromise
Extracted by AI from the linked source. Not reviewed by an editor. How this works
- domain — zz.aiapi2025.top