garak#
Description#
garak checks if an LLM can be made to fail in a way we don’t want. garak probes for hallucination, data leakage, prompt injection, misinformation, toxicity generation, jailbreaks, and many other weaknesses. If you know nmap or msf / Metasploit Framework, garak does somewhat similar things to them, but for LLMs.
Home page for this solution: https://docs.garak.ai/garak
Overview#
Key |
Value |
|---|---|
Name |
garak |
Description |
the LLM vulnerability scanner |
License |
Apache License 2.0 |
Programming Language |
Python |
Created |
2023-05-10 |
Last update |
2025-02-18 |
Github Stars |
3878 |
Project Home Page |
|
Code Repository |
|
OpenSSF Scorecard |
Note:
Created date is date that repro is created on Github.com.
Last update is only the last date I run an automatic check.
Do not attach a wrong value to github stars. Its a vanity metric! Stars count are misleading and don’t indicate if the SBB is high-quality or very popular.