Skip to main content

AIDR API Reference

post/v1/guard_chat_completions
cURL
curl -sSLX POST 'https://api.crowdstrike.com/aidr/aiguard/v1/guard_chat_completions' \
-H 'Authorization: Bearer <your_token>' \
-H 'Content-Type: application/json' \
-d '{}'

This endpoint cannot be called through the documentation site

Guard LLM Chat Completions

POST
https://api.crowdstrike.com/aidr/aiguard/v1/guard_chat_completions

Analyze and redact content to avoid manipulation of the model, addition of malicious content, and other undesirable data transfers.

required parameters

object

'messages' contains Prompt content and role array in JSON format. The content is the multimodel text or image input that will be analyzed. Additional properties such as 'tools' may be provided for analysis.

Click 'Save' to use the value

'messages' contains Prompt content and role array in JSON format. The content is the multimodel text or image input that will be analyzed. Additional properties such as 'tools' may be provided for analysis.

string

Id of source application/agent

Id of source application/agent

string

User/Service account id/service account

User/Service account id/service account

string

Underlying LLM. Example: 'OpenAI'.

Underlying LLM. Example: 'OpenAI'.

string

Model used to perform the event. Example: 'gpt'.

Model used to perform the event. Example: 'gpt'.

string

Model version used to perform the event. Example: '3.5'.

Model version used to perform the event. Example: '3.5'.

string

IP address of user or app or agent.

IP address of user or app or agent.

string

Location of user or app or agent.

Location of user or app or agent.

string

For gateway-like integrations with multi-tenant support.

For gateway-like integrations with multi-tenant support.

string
(default: "input")

(AIDR) Event Type.

(AIDR) Event Type.

string

(AIDR) collector instance id.

(AIDR) collector instance id.

object

(AIDR) Logging schema.

(AIDR) Logging schema.

string

Name of source application/agent.

Name of source application/agent.

string

The group of source application/agent.

The group of source application/agent.

string

Version of the source application/agent.

Version of the source application/agent.

string

Name of subject actor/service account.

Name of subject actor/service account.

string

The group of subject user/actor.

The group of subject user/actor.

string

Geographic region or data center.

Geographic region or data center.

string

Sub tenant of the user or organization

Sub tenant of the user or organization

array<object>

Each item groups tools for a given MCP server.

Click 'Save' to use the value

Each item groups tools for a given MCP server.

string

MCP server name

  • minLength: 1

MCP server name

  • minLength: 1
array<string>
  • minItems: 1

Click 'Save' to use the value

  • minItems: 1
string (base64)

FPE (Format Preserving Encryption) context from a previous guard request. When provided, the encrypted input will be unredacted before processing.

FPE (Format Preserving Encryption) context from a previous guard request. When provided, the encrypted input will be unredacted before processing.

object

Pangea standard response schema

Pangea standard response schema

object
object

Updated structured prompt.

Updated structured prompt.

boolean

Whether or not the prompt triggered a block detection.

Whether or not the prompt triggered a block detection.

boolean

Whether or not the original input was transformed.

Whether or not the original input was transformed.

string

The Policy that was used.

The Policy that was used.

object

Result of the policy analyzing and input prompt.

Result of the policy analyzing and input prompt.

object
boolean

Whether or not the Malicious Prompt was detected.

Whether or not the Malicious Prompt was detected.

object

Details about the analyzers.

Details about the analyzers.

string

The action taken by this Detector

The action taken by this Detector

array<object>

Triggered prompt injection analyzers.

Triggered prompt injection analyzers.

string
number
object
boolean

Whether or not the PII Entities were detected.

Whether or not the PII Entities were detected.

object

Details about the detected entities.

Details about the detected entities.

array<object>

Detected redaction rules.

Detected redaction rules.

string

The action taken on this Entity

The action taken on this Entity

string
string
integer
  • minimum: 0
  • minimum: 0
object
boolean

Whether or not the Malicious Entities were detected.

Whether or not the Malicious Entities were detected.

object

Details about the detected entities.

Details about the detected entities.

array<object>

Detected harmful items.

Detected harmful items.

string
string
integer
  • minimum: 0
  • minimum: 0
object
object
boolean

Whether or not the Custom Entities were detected.

Whether or not the Custom Entities were detected.

object

Details about the detected entities.

Details about the detected entities.

array<object>

Detected redaction rules.

Detected redaction rules.

string

The action taken on this Entity

The action taken on this Entity

string
string
integer
  • minimum: 0
  • minimum: 0
object
boolean

Whether or not the Secret Entities were detected.

Whether or not the Secret Entities were detected.

object

Details about the detected entities.

Details about the detected entities.

array<object>

Detected redaction rules.

Detected redaction rules.

string

The action taken on this Entity

The action taken on this Entity

string
string
integer
  • minimum: 0
  • minimum: 0
object
boolean

Whether or not the Competitors were detected.

Whether or not the Competitors were detected.

object

Details about the detected entities.

Details about the detected entities.

string

The action taken by this Detector

The action taken by this Detector

array<string>

Detected entities.

Detected entities.

object
boolean

Whether or not the Languages were detected.

Whether or not the Languages were detected.

object

Details about the detected languages.

Details about the detected languages.

string

The action taken by this Detector

The action taken by this Detector

array<object>
string
number (float)
  • minimum: 0

  • maximum: 1

  • minimum: 0

  • maximum: 1

object
boolean

Whether or not the Topics were detected.

Whether or not the Topics were detected.

object

Details about the detected topics.

Details about the detected topics.

string

The action taken by this Detector

The action taken by this Detector

array<object>

List of topics detected

List of topics detected

string
number
object
boolean

Whether or not any emojis were detected.

Whether or not any emojis were detected.

object

Details about the detected emojis.

Details about the detected emojis.

string

The action taken by this Detector

The action taken by this Detector

array<object>
string
string
object
boolean

Whether or not the Code was detected.

Whether or not the Code was detected.

object

Details about the detected code.

Details about the detected code.

string

The action taken by this Detector

The action taken by this Detector

string
object

Result of the recipe evaluating configured rules

Result of the recipe evaluating configured rules

object

Details about the evaluation of a single rule, including whether it matched, the action to take, the rule name, and optional debugging information.

Details about the evaluation of a single rule, including whether it matched, the action to take, the rule name, and optional debugging information.

boolean

Whether this rule's logic evaluated to true for the input.

Whether this rule's logic evaluated to true for the input.

string

The action resulting from the rule evaluation. One of 'allowed', 'blocked', or 'reported'.

The action resulting from the rule evaluation. One of 'allowed', 'blocked', or 'reported'.

string

A human-readable name for the rule.

A human-readable name for the rule.

object

The JSON logic expression evaluated for this rule.

The JSON logic expression evaluated for this rule.

object

The input attribute values that were available during rule evaluation.

The input attribute values that were available during rule evaluation.

string (base64)

If an FPE redaction method returned results, this will be the context passed to unredact.

If an FPE redaction method returned results, this will be the context passed to unredact.

string

A unique identifier assigned to each request made to the API. It is used to track and identify a specific request and its associated data. The request_id can be helpful for troubleshooting, auditing, and tracing the flow of requests within the system. It allows users to reference and retrieve information related to a particular request, such as the response, parameters, and raw data associated with that specific request.

"request_id":"prq_x6fdiizbon6j3bsdvnpmwxsz2aan7fqd"

A unique identifier assigned to each request made to the API. It is used to track and identify a specific request and its associated data. The request_id can be helpful for troubleshooting, auditing, and tracing the flow of requests within the system. It allows users to reference and retrieve information related to a particular request, such as the response, parameters, and raw data associated with that specific request.

"request_id":"prq_x6fdiizbon6j3bsdvnpmwxsz2aan7fqd"
string

The timestamp indicates the exact moment when a request is made to the API. It represents the date and time at which the request was initiated by the client. The request_time is useful for tracking and analyzing the timing of requests, measuring response times, and monitoring performance metrics. It allows users to determine the duration between the request initiation and the corresponding response, aiding in the assessment of API performance and latency.

"request_time":"2022-09-21T17:24:33.105Z"

The timestamp indicates the exact moment when a request is made to the API. It represents the date and time at which the request was initiated by the client. The request_time is useful for tracking and analyzing the timing of requests, measuring response times, and monitoring performance metrics. It allows users to determine the duration between the request initiation and the corresponding response, aiding in the assessment of API performance and latency.

"request_time":"2022-09-21T17:24:33.105Z"
string

Duration it takes for the API to process a request and generate a response. It represents the elapsed time from when the request is received by the API to when the corresponding response is returned to the client.

"response_time":"2022-09-21T17:24:34.007Z"

Duration it takes for the API to process a request and generate a response. It represents the elapsed time from when the request is received by the API to when the corresponding response is returned to the client.

"response_time":"2022-09-21T17:24:34.007Z"
string

It represents the status or outcome of the API request made for IP information. It indicates the current state or condition of the request and provides information on the success or failure of the request.

"status":"success"

It represents the status or outcome of the API request made for IP information. It indicates the current state or condition of the request and provides information on the success or failure of the request.

"status":"success"
string

Provides a concise and brief overview of the purpose or primary objective of the API endpoint. It serves as a high-level summary or description of the functionality or feature offered by the endpoint.

Provides a concise and brief overview of the purpose or primary objective of the API endpoint. It serves as a high-level summary or description of the functionality or feature offered by the endpoint.

post/v1/unredact
cURL
curl -sSLX POST 'https://api.crowdstrike.com/aidr/aiguard/v1/unredact' \
-H 'Authorization: Bearer <your_token>' \
-H 'Content-Type: application/json' \
-d '{}'

This endpoint cannot be called through the documentation site

Unredact text or structured JSON

POST
https://api.crowdstrike.com/aidr/aiguard/v1/unredact

Decrypt or unredact fpe redactions

required parameters

Data to unredact

Click 'Save' to use the value

Data to unredact

string (base64)

FPE context used to decrypt and unredact data

FPE context used to decrypt and unredact data

object

Pangea standard response schema

Pangea standard response schema

object

The unredacted data

The unredacted data

string

A unique identifier assigned to each request made to the API. It is used to track and identify a specific request and its associated data. The request_id can be helpful for troubleshooting, auditing, and tracing the flow of requests within the system. It allows users to reference and retrieve information related to a particular request, such as the response, parameters, and raw data associated with that specific request.

"request_id":"prq_x6fdiizbon6j3bsdvnpmwxsz2aan7fqd"

A unique identifier assigned to each request made to the API. It is used to track and identify a specific request and its associated data. The request_id can be helpful for troubleshooting, auditing, and tracing the flow of requests within the system. It allows users to reference and retrieve information related to a particular request, such as the response, parameters, and raw data associated with that specific request.

"request_id":"prq_x6fdiizbon6j3bsdvnpmwxsz2aan7fqd"
string

The timestamp indicates the exact moment when a request is made to the API. It represents the date and time at which the request was initiated by the client. The request_time is useful for tracking and analyzing the timing of requests, measuring response times, and monitoring performance metrics. It allows users to determine the duration between the request initiation and the corresponding response, aiding in the assessment of API performance and latency.

"request_time":"2022-09-21T17:24:33.105Z"

The timestamp indicates the exact moment when a request is made to the API. It represents the date and time at which the request was initiated by the client. The request_time is useful for tracking and analyzing the timing of requests, measuring response times, and monitoring performance metrics. It allows users to determine the duration between the request initiation and the corresponding response, aiding in the assessment of API performance and latency.

"request_time":"2022-09-21T17:24:33.105Z"
string

Duration it takes for the API to process a request and generate a response. It represents the elapsed time from when the request is received by the API to when the corresponding response is returned to the client.

"response_time":"2022-09-21T17:24:34.007Z"

Duration it takes for the API to process a request and generate a response. It represents the elapsed time from when the request is received by the API to when the corresponding response is returned to the client.

"response_time":"2022-09-21T17:24:34.007Z"
string

It represents the status or outcome of the API request made for IP information. It indicates the current state or condition of the request and provides information on the success or failure of the request.

"status":"success"

It represents the status or outcome of the API request made for IP information. It indicates the current state or condition of the request and provides information on the success or failure of the request.

"status":"success"
string

Provides a concise and brief overview of the purpose or primary objective of the API endpoint. It serves as a high-level summary or description of the functionality or feature offered by the endpoint.

Provides a concise and brief overview of the purpose or primary objective of the API endpoint. It serves as a high-level summary or description of the functionality or feature offered by the endpoint.

Status Codes
StatusStatus CodeDescription
InactiveDevice200

Device is not active.

TokenDeletionFailed200

Failed to delete device attached token.

AIDRFieldAliasExists400

Field alias already exists.

AIDRListExists400

List already exists.

AIDRPolicyExists400

Policy already exists.

CSPLogTooLarge400

CSP log is too large.

DeviceExists400

Device already exists.

InvalidAIDRFieldAlias400

Field alias does not exist.

InvalidAIDRListContent400

Unsupported List content.

InvalidAIDRListType400

Unsupported List type.

InvalidAIDRPolicy400

Unsupported Policy content.

InvalidCollectorType400

The operation is not available for this collector type

InvalidDevice400

Device does not exist.

InvalidDeviceId400

The operation is made with invalid device id

InvalidSavedFilter400

Saved filter does not exist.

InvalidSearchId400

The search id is invalid because it has either already been completed and the results have been retrieved, or the search request does not exist.

MissingAIDRList400

List does not exist.

MissingAIDRPolicy400

Policy does not exist.

SavedFilterExists400

Saved filter already exists.

UnsupportedAIDRPolicyVersion400

Unsupported Policy version.

©2026 CrowdStrike. All rights reserved.

PrivacyTerms of UseLegal Notices