security

Detect prompt injection attacks in user-supplied input.

Cost: 1 credit(s). Free tier: 10 calls per IP (no auth).

post/v1/scan/injection

Request

  • Base URL: https://api.agent-toolbox.ai
  • URL: https://api.agent-toolbox.ai/v1/scan/injection
  • Auth: one of:
    • HTTP bearer
    • none

Request body

inputstring required
contextstring

Response

Success.

risk'safe' | 'suspicious' | 'injection' required
scorenumber required
patternsstring[] required
advicestring required
contextstring

Changes

No recorded changes to this operation across all 1 revision of this API.