diff --git a/image/image_analyzer.py b/image/image_analyzer.py
index 62d50aa..33e3198 100755
--- a/image/image_analyzer.py
+++ b/image/image_analyzer.py
@@ -248,6 +248,14 @@ class ImageAnalyzer:
         "多人", "多人脸", "人群", "群像", "合照", "集体照", "全家福", "毕业照", "婚礼合影", "大合照",
         "crowd", "group photo", "many faces",
     )
+    FORBIDDEN_CONTENT_KEYWORDS = (
+        # 党政/涉政
+        "党政", "涉政", "政治人物", "领导人", "国旗", "国徽", "党徽", "党旗", "时政宣传",
+        # 黄暴血腥
+        "黄色", "擦边", "裸露", "色情", "性暗示", "暴力", "凶杀", "打斗", "枪击", "血腥", "尸体", "虐待",
+        # 英文兜底
+        "political", "government propaganda", "nsfw", "porn", "nude", "violence", "bloody", "gore",
+    )
 
     async def analyze(self, image_path: str) -> dict:
         """
@@ -556,9 +564,11 @@ class ImageAnalyzer:
         if perspective not in ("no", "mild", "strong"):
             perspective = "no"
 
+        scene_text = ((subject or "") + " " + (proc_type or "") + " " + (reason or "") + " " + (note or "")).lower()
+
         # 识别“密集文字场景”关键词（中文 + 英文兜底）
         dense_text_scene = any(
-            kw in ((subject or "") + " " + (proc_type or "") + " " + (reason or "")).lower()
+            kw in scene_text
             for kw in self.DENSE_TEXT_SUBJECT_KEYWORDS
         )
 
@@ -638,7 +648,7 @@ class ImageAnalyzer:
             price_suggest = 0
 
         # 硬规则2：多人脸不接；1-2 人脸可做
-        many_faces_scene = any(k in (subject_raw + " " + reason_raw + " " + note_raw).lower() for k in self.MANY_FACES_SUBJECT_KEYWORDS)
+        many_faces_scene = any(k in scene_text for k in self.MANY_FACES_SUBJECT_KEYWORDS)
         if has_face == "yes" and many_faces_scene:
             feasibility = "no"
             risk = "high"
@@ -646,12 +656,19 @@ class ImageAnalyzer:
             reason = (reason or "多人脸") + " | 多人脸场景不接单"
             price_suggest = 0
 
+        # 硬规则3：党政/涉黄/暴力/血腥内容不接单
+        forbidden_scene = any(k in scene_text for k in self.FORBIDDEN_CONTENT_KEYWORDS)
+        sensitive_hit = str(sensitive or "").strip().lower() in ("yes", "true", "1", "是")
+        if forbidden_scene or sensitive_hit:
+            feasibility = "no"
+            risk = "high"
+            note = "含党政/涉黄/暴力/血腥等敏感内容，不接单"
+            reason = (reason or "敏感内容") + " | 敏感内容不接单"
+            price_suggest = 0
+
         # 确保是 5 的倍数
         price_suggest = round(price_suggest / 5) * 5
 
-        if sensitive == "yes":
-            feasibility = "no"
-            note = "图片含敏感内容，不接单"
         risk_label = {"none": "无风险", "low": "低风险", "high": "高风险"}.get(risk, "")
         sens_tag = " | 敏感:是" if sensitive == "yes" else ""
         print(f"[ImageAnalyzer] 识别结果: {complexity} | {reason} | 建议报价: {price_suggest}元{sens_tag}")