Claude in Chrome
Claude in Chrome is a web agent by Anthropic that can interact with web pages. It was found vulnerable to ADI attacks…
Tag: ADI
Antigravity
Antigravity is a web agent by Google that was found vulnerable to ADI attacks. A planted product review could cause it to…
Nanobrowser
Nanobrowser is a web agent that was found vulnerable to ADI attacks. The researchers reported the vulnerability to Nanobrowser but had not…
GPT-5.2
GPT-5.2 is a large language model by OpenAI. It was tested and found vulnerable to Agent Data Injection (ADI) attacks.
GPT-5-mini
GPT-5-mini is a smaller language model by OpenAI. It was tested and found vulnerable to Agent Data Injection (ADI) attacks.
Sonnet 4.5
Sonnet 4.5 is a language model by Anthropic. It was tested and found vulnerable to Agent Data Injection (ADI) attacks.
Gemini Flash
Gemini Flash is a language model by Google. It was tested and found vulnerable to Agent Data Injection (ADI) attacks.
Agent Data Injection (ADI) Attack: How AI Agents Can Be Tricked Into Misclicking or Running Attacker Commands
A new class of attack called Agent Data Injection (ADI) has been disclosed by researchers from Seoul National University, the University of…
Codex
Codex is a coding assistant by OpenAI. It was found vulnerable to ADI attacks where a forged GitHub comment could make it…
Gemini CLI
Gemini CLI is a coding assistant by Google. It was found vulnerable to ADI attacks where a forged GitHub comment could make…