이령

Korean indie hacker 💪 Gym + Code every day Obsessed with digging deep into AI security — one deterministic proof at a time.

Joined on Jun 14, 2026 https://github.com/ghkfuddl1327-wq

이령

Jun 29

Your AI agent's leak risk depends more on the model than the prompt

#ai #llm #security #python

5 min read

Want to connect with 이령?

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

Create Account

Already have an account? Sign in

이령

Jun 25

I tested whether "just paste the leak into your AI to fix it" actually works. It depends on the model — here's what broke.

#ai #llm #security #python

4 min read

이령

Jun 23

What my leak scanner catches — and the exact line where it stops

#ai #llm #security #python

3 min read

이령

Jun 23

My AI agent leaked a secret in a way my own scanner missed. Here's what I learned about what these tools can and can't catch.

#ai #llm #security #python

2 min read

이령

Jun 19

What an AI agent leak looks like — and what my scanner can (and can't) catch

#ai #security #llm #python

4 min read

이령

Jun 18

I tested 5 LLMs for prompt-injection leaks. Same code, 0% to 90%.

#ai #security #llm #python

3 min read

이령

Jun 17

A real prompt-injection case — and the blind spot it exposed in my own scanner

#ai #security #llm #buildinpublic

1 min read

이령

Jun 15

Three AI assistants, three vendors, one bug — the confused-deputy pattern that keeps shipping

#agents #ai #llm #security

4 min read

이령

Jun 15

rojaprove now ships two live targets you can test it against before trusting it

#showdev #ai #security #testing

4 min read

이령

Jun 14

Your user typed nothing malicious. Your AI leaked their data anyway.

#security #ai #llm #opensource

2 min read