AI Guard API Reference

Base URL

ai-guard.<csp>.<region>.pangea.cloud

• OpenAPI Specification

post/v1beta/text/guard

cURL

Code Snippet Language

curl -sSLX POST 'https://ai-guard.aws.us.pangea.cloud/v1beta/text/guard' \
-H 'Authorization: Bearer <your_token>' \
-H 'Content-Type: application/json' \
-d '{}'

Response

Raw Output

200

Code Snippet Language

---

Text Guard for scanning LLM inputs and outputs

POST

https://ai-guard.aws.us.pangea.cloud/v1beta/text/guard

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

fields

text

string

Text to be scanned by AI Guard for PII, sensitive data, malicious content, and other data types defined by the configuration. Supports processing up to 10KB of text.

text

text

recipe

string

(default: "pangea_prompt_guard")

Recipe key of a configuration of data types and settings defined in the Pangea User Console. It specifies the rules that are to be applied to the text, such as defang malicious URLs.

recipe

recipe

debug

boolean

(default: false)

Setting this value to true will provide a detailed analysis of the text data

debug

​

debug

overrides

object

prompt_guard

object

state

string

state

​

state

Response Fields

Response Schema

object

Pangea standard response schema

result

object

redacted_prompt

string

Text that was scanned for redaction

recipe

string

Recipe used to scan the text

findings

object

Result of the recipe analyzing and redacting the text input

prompt_injection_count

integer

Number of prompt injections found in the analysis

malicious_count

integer

Number of texts found to be malicious in the analysis based on the recipe settings

artifact_count

integer

Number of artifacts that matched rules in the analysis

security_issues

object

List of possible security issues discovered in the text

redact_rule_match_count

integer

Number of text strings that match redaction rules from the recipe

malicious_ip_count

integer

Number of malicious IP addresses identified

malicious_domain_count

integer

Number of malicious domains identified

malicious_url_count

integer

Number of malicious URLs identified

compromised_email_addresses

integer

Number of compromised email addresses identified

artifacts

array<object>

List of matches to the recipe's redaction settings, including data type, matched substring, start and end indices, defang status, and verdict as determined by the recipe's redaction rules

type

string

Redaction rule applied, e.g. EMAIL_ADDRESS

value

string

Substring that matches the redaction rule

start

integer

Starting index of the matched substring

end

integer

Ending index of the matched substring

defanged

boolean

Boolean indicating whether the substring was defanged

verdict

string

The verdict, given by the Pangea service, for the indicator

report

request_id

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"

request_time

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"

response_time

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"

status

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"

summary

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.

Status Codes

Status	Status Code	Description
NoProviderConfigured	400	Provider for intelligence services used by ai-guard is not configured
RecipeNotExist	400	Recipe does not exist in the ai-guard configuration

Was this article helpful?

Contact us