Update README.md

README.md

@@ -2,4 +2,10 @@
 license: apache-2.0
 ---
 
-TS-Guard is a guardrail model for step-level tool invocation safety detection. TS-Guard is trained via reinforcement learning with a multi-task reward scheme tailored for agent security, enabling identifying harmful user requests and attack vectors in agent-environment interaction logs, detecting unsafe tool invocation before execution, and providing interpretable analysis and reasoning process
+TS-Guard is a guardrail model for step-level tool invocation safety detection. TS-Guard is trained via reinforcement learning with a multi-task reward scheme tailored for agent security, enabling identifying harmful user requests and attack vectors in agent-environment interaction logs, detecting unsafe tool invocation before execution, and providing interpretable analysis and reasoning process
+
+
+![image](https://cdn-uploads.huggingface.co/production/uploads/66632a3d2dc4dff9a98c38a5/WglXmL5O1Se7L5KuA7T-3.png)
+
+
+![image](https://cdn-uploads.huggingface.co/production/uploads/66632a3d2dc4dff9a98c38a5/AL3z3FcEFwYCyFmWJI9k5.png)