diff --git a/Readme.md b/Readme.md index e0ea01a..6a0b3ae 100644 --- a/Readme.md +++ b/Readme.md @@ -21,26 +21,20 @@
+## Features + +- Customizable Rule Sets or Agent based attacksπ οΈ +- Comprehansive fuzzing for any LLMs π§ͺ +- LLM API integration and stress testing π οΈ +- Wide range of fuzzing and attack techniques π + + +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. + ## About the Project π§
-
-
|
-
-## Features
-
-- Comprehensive Threat Detection π‘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 π: 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 π: Offers detailed reports of vulnerability, helping teams to quickly understand and respond to security incidents.
-- Customizable Rule Sets π οΈ: Allows users to define custom attack rules and parameters to meet specific prompt attacks needs and compliance standards.
-
-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.
## π¦ Installation