add jailbreak attempt detection guardrail category

litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/categories/prompt_injection_jailbreak.yaml

@@ -0,0 +1,140 @@
+# Jailbreak Attempt Detection - Detects common jailbreak patterns
+# Uses conditional logic: BLOCK if an identifier word + block word appear in same sentence
+category_name: "prompt_injection_jailbreak"
+description: "Detects jailbreak attempts including DAN, roleplay attacks, and safety bypass requests"
+default_action: "BLOCK"
+
+# IDENTIFIER WORDS - Roleplay/persona manipulation actions
+identifier_words:
+  - "pretend"
+  - "roleplay"
+  - "act as"
+  - "imagine you are"
+  - "suppose you are"
+  - "you are now"
+  - "behave as"
+  - "respond as"
+  - "simulate"
+  - "emulate"
+  - "impersonate"
+  - "transform into"
+  - "become"
+  - "play the role"
+  - "switch to"
+  - "enter"
+  - "enable"
+  - "activate"
+  - "turn on"
+
+# ADDITIONAL BLOCK WORDS - Jailbreak-related terms
+additional_block_words:
+  - "no restrictions"
+  - "no rules"
+  - "no guidelines"
+  - "no filters"
+  - "no limitations"
+  - "no boundaries"
+  - "no censorship"
+  - "no moderation"
+  - "no safety"
+  - "no ethical"
+  - "bypass"
+  - "override"
+  - "unrestricted"
+  - "unfiltered"
+  - "uncensored"
+  - "unmoderated"
+  - "unlimited"
+  - "without limits"
+  - "without restrictions"
+  - "without rules"
+  - "without guidelines"
+  - "without filters"
+  - "anything mode"
+  - "god mode"
+  - "developer mode"
+  - "debug mode"
+  - "test mode"
+  - "admin mode"
+  - "root mode"
+  - "superuser"
+  - "evil mode"
+  - "chaos mode"
+  - "unrestricted mode"
+  - "opposite mode"
+
+# ALWAYS BLOCK - Explicit jailbreak patterns (blocked regardless of context)
+always_block_keywords:
+  # DAN and known jailbreaks
+  - keyword: "DAN mode"
+    severity: "high"
+  - keyword: "Do Anything Now"
+    severity: "high"
+  - keyword: "developer mode enabled"
+    severity: "high"
+  - keyword: "jailbreak"
+    severity: "high"
+  - keyword: "jailbroken"
+    severity: "high"
+  - keyword: "bypass safety"
+    severity: "high"
+  - keyword: "bypass filters"
+    severity: "high"
+  - keyword: "bypass content filter"
+    severity: "high"
+  - keyword: "bypass moderation"
+    severity: "high"
+  - keyword: "ignore safety guidelines"
+    severity: "high"
+  - keyword: "ignore content policy"
+    severity: "high"
+  - keyword: "ignore ethical guidelines"
+    severity: "high"
+  - keyword: "without restrictions"
+    severity: "medium"
+  - keyword: "without safety"
+    severity: "high"
+  - keyword: "without filters"
+    severity: "medium"
+  - keyword: "remove all restrictions"
+    severity: "high"
+  - keyword: "disable safety"
+    severity: "high"
+  - keyword: "disable content filter"
+    severity: "high"
+  - keyword: "disable moderation"
+    severity: "high"
+  - keyword: "turn off safety"
+    severity: "high"
+  - keyword: "turn off filters"
+    severity: "high"
+
+  # Token smuggling / encoding tricks
+  - keyword: "respond in base64"
+    severity: "high"
+  - keyword: "encode your response"
+    severity: "medium"
+  - keyword: "answer in rot13"
+    severity: "high"
+  - keyword: "respond in hex"
+    severity: "high"
+  - keyword: "use pig latin"
+    severity: "medium"
+  - keyword: "respond backwards"
+    severity: "medium"
+  - keyword: "spell it out letter by letter"
+    severity: "medium"
+
+# Exception patterns (legitimate uses)
+exceptions:
+  - "jailbreak prevention"
+  - "security research"
+  - "red team"
+  - "red teaming"
+  - "AI safety research"
+  - "AI alignment"
+  - "prompt injection defense"
+  - "how to prevent jailbreaks"
+  - "jailbreak detection"
+  - "content moderation research"
+  - "safety evaluation"