security

Prompt Injection Detection

Classify agent-bound text for prompt injection: a safe, suspicious, or malicious verdict with the patterns that matched. POST /v1/prompt with {text} and get the classification as one JSON object. Deterministic per ruleset version. Pay per request in USDC; no account, no API key.

post/v1/prompt-injection-detect

Request

  • Base URL: https://agent.pocket.network
  • URL: https://agent.pocket.network/v1/prompt-injection-detect
  • Auth: none required

Request body

textstring required

The agent-bound text to inspect.

Response

The upstream response, served after payment settles.

object required

For POST /v1/prompt, a JSON object with the verdict and a matches array of the patterns that fired. The exact shape is the service's own and is not pinned here; errors return a JSON object with an error field, and the GET routes return their own small JSON documents.

Changes

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