prompt-guard-intel__scan_prompt_risk

Active

declared in 1.0.0

[prompt-guard-intel] Scan prompt text for injection phrases, data-exfiltration requests, role confusion, hidden encoding, and unsafe tool instructions.

Parameters schema

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Prompt, web text, or retrieved context to scan."
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

TO1 Intelligence Fleet

1/7 registries

View full server →