Forem

Dongha Koo profile picture

Dongha Koo

Backend developer building open-source AI security tools. Creator of Aegis.

Location Seoul, South Korea Joined Joined on  Personal website https://github.com/Acacian/aegis github website
I Tested 9 AI Agent Frameworks for Basic Security. None of Them Passed.

I Tested 9 AI Agent Frameworks for Basic Security. None of Them Passed.

Comments
4 min read

Want to connect with Dongha Koo?

Create an account to connect with Dongha Koo. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
I Poisoned My Own MCP Server in 5 Minutes. Here's How.

I Poisoned My Own MCP Server in 5 Minutes. Here's How.

4
Comments 3
5 min read
LangChain Hit with 3 Critical CVEs — Why Your AI Agents Need a Governance Layer

LangChain Hit with 3 Critical CVEs — Why Your AI Agents Need a Governance Layer

1
Comments
3 min read
Your LangChain Agent Has No Security. Neither Does CrewAI, OpenAI, or 6 Others.

Your LangChain Agent Has No Security. Neither Does CrewAI, OpenAI, or 6 Others.

2
Comments
4 min read
Your AI Agent Can Be Hijacked With 3 Lines of JSON

Your AI Agent Can Be Hijacked With 3 Lines of JSON

7
Comments 16
4 min read
EU AI Act Compliance in 47 Lines of Python

EU AI Act Compliance in 47 Lines of Python

Comments
3 min read
loading...