hugobatista/unicode-injection

Proof of concept demonstrating Unicode injection vulnerabilities using invisible characters to manipulate Large Language Models (LLMs) and AI assistants (e.g., Claude, AI Studio) via hidden prompts or data poisoning. Educational/research purposes only.

27
/ 100
Experimental
No License No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 1 / 25
Community 12 / 25

How are scores calculated?

Stars

5

Forks

1

Language

License

Last pushed

Jan 27, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/hugobatista/unicode-injection"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.