BackdoorAgent

by Yunhao-Feng · Agent Tool · ★ 30

About BackdoorAgent

BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically inject, track, and evaluate backdoor triggers across multi-step trajectories using unified metrics like ASR and clean accuracy.

Quick Facts

Stars30
Forks1
LanguagePython
CategoryAgent Tool
LicenseApache-2.0
Quality Score31.55/100
Open Issues1
Last Updated2026-03-16
Created2026-01-09
Platformspython
Est. Tokens~1857k

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is BackdoorAgent?

BackdoorAgent is BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically inject, track, and evaluate backdoor triggers across multi-step . It is categorized as a Agent Tool with 30 GitHub stars.

What programming language is BackdoorAgent written in?

BackdoorAgent is primarily written in Python.

How do I install or use BackdoorAgent?

You can find installation instructions and usage details in the BackdoorAgent GitHub repository at github.com/Yunhao-Feng/BackdoorAgent. The project has 30 stars and 1 forks, indicating an active community.

What license does BackdoorAgent use?

BackdoorAgent is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

View on GitHub → Browse Agent Tool tools