From e1e3fa871224b137c7ea95ad8e2e387c33bb269b Mon Sep 17 00:00:00 2001 From: Alexander Myasoedov Date: Fri, 26 Apr 2024 21:32:47 +0300 Subject: [PATCH] feat(Update readme): --- Readme.md | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/Readme.md b/Readme.md index e0ea01a..6a0b3ae 100644 --- a/Readme.md +++ b/Readme.md @@ -21,26 +21,20 @@

-## About the Project πŸ§™ +## Features -booking-screen +- Customizable Rule Sets or Agent based attacksπŸ› οΈ +- Comprehansive fuzzing for any LLMs πŸ§ͺ +- LLM API integration and stress testing πŸ› οΈ +- Wide range of fuzzing and attack techniques πŸŒ€ -

-

LLM threat vectors scanner

-| | | -| --- | --- | -| Prebuilt Datasets of Prompts


Focused on OWASP top 10 LLM


Integration under 1 min
| | +Note: Please be aware that Agentic Security is designed as a safety scanner tool and not a foolproof solution. It cannot guarantee complete protection against all possible threats. -## Features +## About the Project πŸ§™ -- Comprehensive Threat Detection πŸ›‘οΈ: Scans for a wide array of LLM vulnerabilities including prompt injection, jailbreaking, hallucinations, biases, and other malicious exploitation attempts. -- OWASP Top 10 for LLMs scan: to test the list of the most critical LLM vulnerabilities. -- Privacy-centric Architecture πŸ”’: Ensures that all data scanning and analysis occur on-premise or in a local environment, with no external data transmission, maintaining strict data privacy. -- Comprehensive Reporting Tools πŸ“Š: Offers detailed reports of vulnerability, helping teams to quickly understand and respond to security incidents. -- Customizable Rule Sets πŸ› οΈ: Allows users to define custom attack rules and parameters to meet specific prompt attacks needs and compliance standards. +booking-screen -Note: Please be aware that Agentic Security is designed as a safety scanner tool and not a foolproof solution. It cannot guarantee complete protection against all possible threats. ## πŸ“¦ Installation