diff --git a/plugins/banwords/README.md b/plugins/banwords/README.md
index c423a36..39517f6 100644
--- a/plugins/banwords/README.md
+++ b/plugins/banwords/README.md
@@ -1,9 +1,27 @@
+
 ## 插件描述
+
 简易的敏感词插件，暂不支持分词，请自行导入词库到插件文件夹中的`banwords.txt`，每行一个词，一个参考词库是[1](https://github.com/cjh0613/tencent-sensitive-words/blob/main/sensitive_words_lines.txt)。
 
-`config.json`中能够填写默认的处理行为，目前行为有：
+使用前将`config.json.template`复制为`config.json`，并自行配置。
+
+目前插件对消息的默认处理行为有如下两种：
+
 - `ignore` : 无视这条消息。
 - `replace` : 将消息中的敏感词替换成"*"，并回复违规。
 
+```json
+    "action": "replace",  
+    "reply_filter": true,
+    "reply_action": "ignore"
+```
+
+在以上配置项中：
+
+- `action`: 对用户消息的默认处理行为
+- `reply_filter`: 是否对ChatGPT的回复也进行敏感词过滤
+- `reply_action`: 如果开启了回复过滤，对回复的默认处理行为
+
 ## 致谢
+
 搜索功能实现来自https://github.com/toolgood/ToolGood.Words
\ No newline at end of file
diff --git a/plugins/banwords/banwords.py b/plugins/banwords/banwords.py
index e2719d6..2d94af4 100644
--- a/plugins/banwords/banwords.py
+++ b/plugins/banwords/banwords.py
@@ -36,6 +36,9 @@ class Banwords(Plugin):
                         words.append(word)
             self.searchr.SetKeywords(words)
             self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
+            if conf.get("reply_filter",True):
+                self.handlers[Event.ON_DECORATE_REPLY] = self.on_decorate_reply
+                self.reply_action = conf.get("reply_action","ignore")
             logger.info("[Banwords] inited")
         except Exception as e:
             logger.warn("[Banwords] init failed, ignore or see https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins/banwords .")
@@ -53,7 +56,7 @@ class Banwords(Plugin):
         if self.action == "ignore":
             f = self.searchr.FindFirst(content)
             if f:
-                logger.info("Banwords: %s" % f["Keyword"])
+                logger.info("[Banwords] %s in message" % f["Keyword"])
                 e_context.action = EventAction.BREAK_PASS
                 return
         elif self.action == "replace":
@@ -63,5 +66,26 @@ class Banwords(Plugin):
                 e_context.action = EventAction.BREAK_PASS
                 return
             
+    def on_decorate_reply(self, e_context: EventContext):
+
+        if e_context['reply'].type not in [ReplyType.TEXT]:
+            return
+        
+        reply = e_context['reply']
+        content = reply.content
+        if self.reply_action == "ignore":
+            f = self.searchr.FindFirst(content)
+            if f:
+                logger.info("[Banwords] %s in reply" % f["Keyword"])
+                e_context['reply'] = None
+                e_context.action = EventAction.BREAK_PASS
+                return
+        elif self.reply_action == "replace":
+            if self.searchr.ContainsAny(content):
+                reply = Reply(ReplyType.INFO, "已替换回复中的敏感词: \n"+self.searchr.Replace(content))
+                e_context['reply'] = reply
+                e_context.action = EventAction.CONTINUE
+                return
+    
     def get_help_text(self, **kwargs):
         return Banwords.desc
\ No newline at end of file
diff --git a/plugins/banwords/config.json.template b/plugins/banwords/config.json.template
index 000fdda..8b4d3d1 100644
--- a/plugins/banwords/config.json.template
+++ b/plugins/banwords/config.json.template
@@ -1,3 +1,5 @@
 {
-    "action": "ignore"
+    "action": "replace",
+    "reply_filter": true,
+    "reply_action": "ignore"
 }
\ No newline at end of file