interactions-v1_other
Interactions
Performs a detailed security analysis of the input and/or output of LLM interactions.
post/detection/v1/interactions
Headers
HL-Project-Idstring
The ID or alias for the Project to govern the request processing.
Request body
Example request
{
"metadata": {
"model": "gpt-5",
"requester_id": "user-1234",
"provider": "openai"
},
"input": {
"messages": [
{
"role": "user",
"content": "What the largest moon of jupiter?"
}
]
},
"output": {
"messages": [
{
"role": "assistant",
"content": "The largest moon of Jupiter is Ganymede."
}
]
}
}Response
Successful Response
Example response
{
"metadata": {
"event_id": "d290f1ee-6c54-4b01-90e6-d701748f0851",
"analyzed_at": "2023-10-10T14:48:00.000Z",
"provider": "openai",
"model": "gpt-5",
"requester_id": "user-1234",
"project": {
"project_id": "ca87b009-90bd-4724-91c2-f23326acd51a",
"project_alias": "enterprise-search",
"ruleset_id": "b5d7d261-b7be-451a-b943-0d408ab88aab"
},
"processing_time_ms": 15.34
},
"analysis": [
{
"id": "prompt_injection.5.input",
"name": "prompt_injection",
"phase": "input",
"version": 5,
"configuration": {
"enabled": true,
"scan_type": "full",
"allow_overrides": {},
"block_overrides": {}
},
"detected": true,
"findings": {
"frameworks": {
"mitre": [
{
"label": "AML.T0051",
"name": "LLM Prompt Injection"
}
],
"owasp": [
{
"label": "LLM01",
"name": "Prompt Injection"
}
],
"owasp:2025": [
{
"label": "LLM01:2025",
"name": "Prompt Injection"
}
]
},
"probabilities": [
1
]
},
"processing_time_ms": 7.01
}
],
"analyzed_data": {
"input": {
"messages": [
{
"role": "user",
"content": "What the largest moon of jupiter?"
}
]
},
"output": {
"messages": [
{
"role": "assistant",
"content": "The largest moon of Jupiter is Ganymede."
}
]
}
},
"modified_data": {
"input": {
"messages": [
{
"role": "user",
"content": "What the largest moon of jupiter?"
}
]
},
"output": {
"messages": [
{
"role": "assistant",
"content": "The largest moon of Jupiter is Ganymede."
}
]
}
}
}