scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-08-28 05:25:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

add prompt injection detection policy template

Browse source
This commit is contained in:
Ishaan Jaffer 2026-02-17 20:28:02 -08:00
parent 60bcf2086c
commit 021d675b4d
1 changed files with 121 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

121
litellm/policy_templates_backup.json
View file

@ -831,5 +831,126 @@
],
"guardrails_remove": []
}
},
{
"id": "prompt-injection-detection",
"title": "Prompt Injection Detection",
"description": "Detects and blocks prompt injection attacks including SQL injection, malicious code injection, system prompt extraction, jailbreak attempts, and data exfiltration. Applies pre-call screening to block attacks before they reach the LLM.",
"region": "Global",
"icon": "ShieldExclamationIcon",
"iconColor": "text-red-500",
"iconBg": "bg-red-50",
"guardrails": [
"prompt-injection-sql",
"prompt-injection-malicious-code",
"prompt-injection-system-prompt",
"prompt-injection-jailbreak",
"prompt-injection-data-exfiltration"
],
"complexity": "Medium",
"guardrailDefinitions": [
{
"guardrail_name": "prompt-injection-sql",
"litellm_params": {
"guardrail": "litellm_content_filter",
"mode": "pre_call",
"categories": [
{
"category": "prompt_injection_sql",
"enabled": true,
"action": "BLOCK",
"severity_threshold": "medium"
}
]
},
"guardrail_info": {
"description": "Blocks SQL injection attempts in prompts (DROP TABLE, UNION SELECT, OR 1=1, etc.)"
}
},
{
"guardrail_name": "prompt-injection-malicious-code",
"litellm_params": {
"guardrail": "litellm_content_filter",
"mode": "pre_call",
"categories": [
{
"category": "prompt_injection_malicious_code",
"enabled": true,
"action": "BLOCK",
"severity_threshold": "medium"
}
]
},
"guardrail_info": {
"description": "Blocks malicious code injection attempts (shell commands, reverse shells, script injection, encoded payloads)"
}
},
{
"guardrail_name": "prompt-injection-system-prompt",
"litellm_params": {
"guardrail": "litellm_content_filter",
"mode": "pre_call",
"categories": [
{
"category": "prompt_injection_system_prompt",
"enabled": true,
"action": "BLOCK",
"severity_threshold": "medium"
}
]
},
"guardrail_info": {
"description": "Blocks system prompt extraction and instruction override attempts (ignore previous instructions, reveal your prompt, etc.)"
}
},
{
"guardrail_name": "prompt-injection-jailbreak",
"litellm_params": {
"guardrail": "litellm_content_filter",
"mode": "pre_call",
"categories": [
{
"category": "prompt_injection_jailbreak",
"enabled": true,
"action": "BLOCK",
"severity_threshold": "medium"
}
]
},
"guardrail_info": {
"description": "Blocks jailbreak attempts (DAN mode, developer mode, safety bypass, token smuggling)"
}
},
{
"guardrail_name": "prompt-injection-data-exfiltration",
"litellm_params": {
"guardrail": "litellm_content_filter",
"mode": "pre_call",
"categories": [
{
"category": "prompt_injection_data_exfiltration",
"enabled": true,
"action": "BLOCK",
"severity_threshold": "medium"
}
]
},
"guardrail_info": {
"description": "Blocks data exfiltration attempts (extract training data, dump database, steal credentials, etc.)"
}
}
],
"templateData": {
"policy_name": "prompt-injection-detection",
"description": "Prompt injection detection policy. Blocks SQL injection, malicious code injection, system prompt extraction, jailbreak attempts, and data exfiltration in prompts before they reach the LLM.",
"guardrails_add": [
"prompt-injection-sql",
"prompt-injection-malicious-code",
"prompt-injection-system-prompt",
"prompt-injection-jailbreak",
"prompt-injection-data-exfiltration"
],
"guardrails_remove": []
}
}
]