List security policies
Updated at:
Query the security policy list. 11 policies in total, fixed and returned in full, no pagination.
Prerequisites
Configure the endpoint and authentication first. See API overview and authentication.
Endpoint
GET /policies
Query the security policy list. 11 policies in total, fixed and returned in full, no pagination.
Request example
curl -X GET "$BASE_URL/policies" \
-H "Authorization: Bearer $BAILIAN_API_KEY"
BASE_URL is https://{workspace_id}.cn-beijing.maas.aliyuncs.com/api/v1/agentstudio/security, and BAILIAN_API_KEY is your Alibaba Cloud Bailian API Key.
Response body
| Field | Type | Description |
|---|---|---|
policy_code | string | Policy identifier, see the table below |
risk_domain | string | Policy group, see the table below |
enabled | boolean | true enabled, false disabled |
free | boolean | Whether it is a free capability. Free policies remain effective before advanced protection is activated |
policy_code values:
| policy_code | risk_domain | Name |
|---|---|---|
| content_safety | model_interaction | Content Security |
| prompt_attack | model_interaction | Prompt Attack |
| sensitive_data_leak | model_interaction | Sensitive Data Leakage |
| tool_invoke | runtime_tool | Tool Call Security |
| skill_scan | runtime_tool | Skills Security Detection |
| network_protection | runtime_tool | Network Protection |
| rag_poisoning | knowledge_memory | RAG Data Poisoning |
| memory_theft | knowledge_memory | Memory Theft |
| identity_credential | identity_credential | Identity and Credential Security |
| baseline_check | config_component | Baseline Check (free) |
| vulnerability_scan | config_component | Vulnerability Scan (free) |
risk_domain values: model_interaction, runtime_tool, knowledge_memory, identity_credential, config_component.
Response example
{
"success": true,
"data": [
{"policy_code": "content_safety", "risk_domain": "model_interaction", "enabled": false, "free": false},
{"policy_code": "prompt_attack", "risk_domain": "model_interaction", "enabled": true, "free": false},
{"policy_code": "sensitive_data_leak", "risk_domain": "model_interaction", "enabled": true, "free": false},
{"policy_code": "tool_invoke", "risk_domain": "runtime_tool", "enabled": true, "free": false},
{"policy_code": "skill_scan", "risk_domain": "runtime_tool", "enabled": true, "free": false},
{"policy_code": "network_protection", "risk_domain": "runtime_tool", "enabled": false, "free": false},
{"policy_code": "rag_poisoning", "risk_domain": "knowledge_memory", "enabled": true, "free": false},
{"policy_code": "memory_theft", "risk_domain": "knowledge_memory", "enabled": true, "free": false},
{"policy_code": "identity_credential", "risk_domain": "identity_credential", "enabled": true, "free": false},
{"policy_code": "baseline_check", "risk_domain": "config_component", "enabled": true, "free": true},
{"policy_code": "vulnerability_scan", "risk_domain": "config_component", "enabled": true, "free": true}
]
}
Is this page helpful?