add data exfiltration detection guardrail category

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

@@ -0,0 +1,123 @@
+# Data Exfiltration Detection - Detects attempts to extract sensitive data via prompts
+# Uses conditional logic: BLOCK if an identifier word + block word appear in same sentence
+category_name: "prompt_injection_data_exfiltration"
+description: "Detects attempts to extract training data, internal information, or user data through prompts"
+default_action: "BLOCK"
+
+# IDENTIFIER WORDS - Data access and extraction actions
+identifier_words:
+  - "extract"
+  - "leak"
+  - "exfiltrate"
+  - "dump"
+  - "retrieve"
+  - "access"
+  - "steal"
+  - "obtain"
+  - "harvest"
+  - "scrape"
+  - "collect"
+  - "gather"
+  - "expose"
+  - "export"
+  - "download"
+  - "copy"
+  - "siphon"
+
+# ADDITIONAL BLOCK WORDS - Sensitive data targets
+additional_block_words:
+  - "training data"
+  - "training set"
+  - "training examples"
+  - "internal data"
+  - "internal information"
+  - "database contents"
+  - "database records"
+  - "user data"
+  - "user records"
+  - "user information"
+  - "personal data"
+  - "private information"
+  - "private data"
+  - "confidential data"
+  - "confidential information"
+  - "sensitive data"
+  - "sensitive information"
+  - "customer data"
+  - "customer records"
+  - "employee data"
+  - "employee records"
+  - "credentials"
+  - "passwords"
+  - "API keys"
+  - "access tokens"
+  - "secret keys"
+  - "encryption keys"
+  - "private keys"
+  - "session tokens"
+  - "authentication tokens"
+  - "model weights"
+  - "model parameters"
+  - "source code"
+  - "proprietary code"
+  - "intellectual property"
+
+# ALWAYS BLOCK - Explicit data exfiltration patterns (blocked regardless of context)
+always_block_keywords:
+  - keyword: "extract training data"
+    severity: "high"
+  - keyword: "leak internal data"
+    severity: "high"
+  - keyword: "dump database"
+    severity: "high"
+  - keyword: "dump all records"
+    severity: "high"
+  - keyword: "show all user data"
+    severity: "high"
+  - keyword: "list all users"
+    severity: "medium"
+  - keyword: "list all passwords"
+    severity: "high"
+  - keyword: "show all API keys"
+    severity: "high"
+  - keyword: "reveal all credentials"
+    severity: "high"
+  - keyword: "expose customer data"
+    severity: "high"
+  - keyword: "steal user information"
+    severity: "high"
+  - keyword: "exfiltrate data"
+    severity: "high"
+  - keyword: "harvest email addresses"
+    severity: "high"
+  - keyword: "scrape personal information"
+    severity: "high"
+  - keyword: "extract model weights"
+    severity: "high"
+  - keyword: "steal source code"
+    severity: "high"
+  - keyword: "copy proprietary code"
+    severity: "high"
+  - keyword: "download private data"
+    severity: "high"
+  - keyword: "access confidential files"
+    severity: "high"
+  - keyword: "retrieve secret keys"
+    severity: "high"
+
+# Exception patterns (legitimate uses)
+exceptions:
+  - "data extraction pipeline"
+  - "ETL"
+  - "data science"
+  - "data engineering"
+  - "data migration"
+  - "backup and recovery"
+  - "data export feature"
+  - "GDPR data request"
+  - "right to access"
+  - "data portability"
+  - "legitimate data access"
+  - "authorized data retrieval"
+  - "data loss prevention"
+  - "DLP"