prompt_injection_scan

Active

Tool of IA-QA — 130+ QA & Dev Tools for AI Agents

declared in 1.0.0

Scan user input or prompts for common prompt injection patterns. Detects system prompt overrides, jailbreak attempts, role manipulation, encoding tricks, delimiter attacks, template/interpolation injection ({{...}}, ${...}), and context-exfiltration attempts ("repeat everything above").

Parameters schema

{
  "type": "object",
  "required": [
    "input"
  ],
  "properties": {
    "input": {
      "type": "string",
      "description": "The user input or prompt to scan for injection patterns"
    },
    "sensitivity": {
      "enum": [
        "low",
        "medium",
        "high"
      ],
      "type": "string",
      "description": "Detection sensitivity (default: medium)"
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.50.

Parent server

IA-QA — 130+ QA & Dev Tools for AI Agents

https://github.com/jcjamet/ia-qa

1/7 registries

View full server →