Evan R. Murphy comments on ChatGPT Plugins—The Beginning of the End

[Evan R. Murphy]

The repo https://​​github.com/​​greshake/​​llm-security proposes that there are big security issues with LLMs having a plugins API:

We demonstrate potentially brutal consequences of giving LLMs like ChatGPT interfaces to other applications. We propose newly enabled attack vectors and techniques and provide demonstrations of each in this repository:

• Remote control of chat LLMs

• Leaking/​exfiltrating user data

• Persistent compromise across sessions

• Spread injections to other LLMs

• Compromising LLMs with tiny multi-stage payloads

• Automated Social Engineering

• Targeting code completion engines

Based on our findings:

1. Prompt injections can be as powerful as arbitrary code execution

2. Indirect prompt injections are a new, much more powerful way of delivering injections.