# sail-sg/agent-smith

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/sail-sg-agent-smith).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

122 stars · 14 forks · Python · MIT

## Links

- GitHub: https://github.com/sail-sg/Agent-Smith
- Homepage: https://sail-sg.github.io/Agent-Smith/
- awesome-repositories: https://awesome-repositories.com/repository/sail-sg-agent-smith.md

## Description

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

## Tags

### Part of an Awesome List

- [Jailbreak Attack Methods](https://awesome-repositories.com/f/awesome-lists/security/jailbreak-attack-methods.md) — Rapidly jailbreaking multimodal agents using single adversarial images.