---
title: "Verify a Prompt"
method: POST
path: "/wall"
---

# Verify a Prompt

`POST /wall`

This endpoint accepts a text prompt, strips PII, and checks it for prompt injection, returning an injection score.

## Request body

- WallRequest
  - `user_id` string — The user ID of the user who is submitting the prompt. This is used to flag suspicious users
  - `session_id` string — The session ID of the user who is submitting the prompt. This is used to flag suspicious sessions
  - `prompt` string, required — The text prompt to be verified.
  - `scan_pii` boolean — Whether to scan for PII in the prompt.
  - `xml_tag` string — The XML tag that is used to escape user input in your prompt (this may have been generated with keep).
  - `check_badwords` boolean — Whether to scan for badwords in the prompt.
  - `fast_check` boolean — Whether to perform a fast check on the prompt instead of a full check.

## Response `200`

Successful operation.

- WallResponse
  - `contains_pii` boolean — Whether the prompt contains PII.
  - `potential_jailbreak` boolean — Whether the prompt contains a potential jailbreak.
  - `potential_xml_escaping` boolean — Whether the prompt contains potential XML escaping.
  - `suspicious_user` boolean — Whether the user is suspicious.
  - `suspicious_session` boolean — Whether the session is suspicious.
  - `modified_prompt` string — The prompt, modified in some way - e.g. by summarising it as per the configuration specified in the request.

## Other responses

- `400` — Bad request. The prompt field is missing or invalid.
- `500` — Internal server error.

---

[API](https://skmtc.net/safetorun/apis/promptdefender-pii-and-prompt-injection-verification-service.md) · [All operations](https://skmtc.net/safetorun/apis/promptdefender-pii-and-prompt-injection-verification-service/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/safetorun/promptdefender-pii-and-prompt-injection-verification-service/revisions/d7e556f931cd/schema)