prompt_injection_check
Prompt-injection risk check for agents: GET ?url= scans a public page (visible and hidden text, comments, attributes, meta, JSON-LD) or POST JSON {"text"} (max 50 KB) scans raw text. Flags instruction overrides, role/system-prompt spoofing, secret exfiltration asks, tool-call coercion, hidden or unicode-smuggled text, base64 instructions and markdown image exfil links. Returns a 0-100 risk score, low/medium/high verdict and findings. Heuristic; not charged on failure. — $0.002 USDC per call via x402 v2 (Base or Solana).
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "prompt_injection_check"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | Public http(s) URL of the page to scan (use this or text) | |
| text | No | Raw text/Markdown/HTML to scan instead of a URL (max 50 KB; best sent as POST JSON body) |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | ||
| url | No | ||
| note | No | ||
| advice | No | ||
| counts | No | ||
| source | No | ||
| verdict | No | ||
| findings | No | ||
| final_url | No | ||
| risk_score | No |