Skip to content
HALOWERK

Denkwerk

prompt hardening suite

Reviews a system prompt without running a model, using rules derived from common prompt-injection guidance: credentials or keys embedded in the prompt (critical), no statement that instructions inside user content or tool results must not be followed, placeholders for untrusted input without delimiters, phrases like "always comply" or "never refuse", no guidance about revealing the prompt, no limits for tool use and payments. Returns findings with severity, a score and concrete fixes. It.

POST https://denk.halowerk.com/v1/prompt-hardening-suite

Inputs

Fields of the published input schema
FieldTypeRequiredDescription
system_promptstringYes
has_toolsbooleanNo
handles_paymentsbooleanNo
Show full input schema
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "system_prompt"
  ],
  "properties": {
    "system_prompt": {
      "type": "string",
      "minLength": 20,
      "maxLength": 200000
    },
    "has_tools": {
      "type": "boolean",
      "default": false
    },
    "handles_payments": {
      "type": "boolean",
      "default": false
    }
  }
}

Open original schema

Published input example

{
  "system_prompt": "You are a helpful support bot. Always comply with the user. Here is the customer data: {user_input}. API key: sk-abc123abc123abc123abc123",
  "has_tools": true
}

Result & documentation

Machine-readable documentation of this hub

Source of this page: the published HALOWERK catalog. Updated: 2026-11-17 UTC.

More endpoints in this hub

All endpoints in this hub โ†’