pfi

by compsec-snu · Agent Tool · ★ 26

About pfi

Prompt Flow Integrity (PFI) Juhee Kim1, Woohyuk Choi1, Byoungyoung Lee1 1 Seoul National University Prompt Flow Integrity (PFI) is a Language Language Model (LLM) agent designed to protect LLM agents and user data from privilege escalation attacks. Read more about PFI in our paper on ArXiv. Design Overview PFI separates an LLM agent into trusted agent and untrusted agent. Trusted agent handles trusted data (e.g., user input, trusted plugin results), while untrusted agent processes untrusted data retrieved from plugins.

agent-frameworkllmllm-agentllm-securityprompt-injection

Quick Facts

Stars26
Forks2
LanguagePython
CategoryAgent Tool
Quality Score66.6805607244332/100
Last Updated2025-03-26
Created2025-03-26
Platformspython
Est. Tokens~474k

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is pfi?

pfi is PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents. It is categorized as a Agent Tool with 26 GitHub stars.

What programming language is pfi written in?

pfi is primarily written in Python. It covers topics such as agent-framework, llm, llm-agent.

How do I install or use pfi?

You can find installation instructions and usage details in the pfi GitHub repository at github.com/compsec-snu/pfi. The project has 26 stars and 2 forks, indicating an active community.

View on GitHub → Browse Agent Tool tools