# AI Security Guard Document Scanner

> AI Security Guard Document Scanner is a paid API for AI agents from aisecurityguard.io, paid per call via x402, $0.12/call, status unknown (last checked 2026-09-15).

Scans documents (e.g. PDFs) for hidden text, prompt injection payloads, and other malicious content that could compromise autonomous AI agents

## Facts

- Endpoint: POST https://aisecurityguard.io/v1/document/scan
- Price: $0.12/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/ai-security-guard-document-scanner-64de34a9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_X_wZWT7bY7HSTSTFuYEI0

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability ai-security-guard-document-scanner-64de34a9 -d '<json body>'
```

Example prompt: Before you process this PDF I just received, can you scan it for hidden text or prompt injection attacks — I want a verdict on whether it's suspicious and a list of any findings with their severity?

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests user-supplied or third-party documents (especially PDFs) and you need to detect hidden instructions, annotation-layer injections, or other adversarial content before passing the document to an LLM. Ideal for agentic workflows where untrusted documents could hijack the agent's behavior via embedded prompt injection.

## Known failure modes

- Unsupported file format — only certain document types accepted
- Document too large — size limits may apply
- Malformed or corrupted document — parsing failure
- Rate limit exceeded — too many scans in a short window
- Payment failure — insufficient USDC balance for x402 transaction

## How this service works

Knowledge, understanding, and tooling is power. Research-backed education on agentic security, free resources, then AgentGuard360 and Protection SDK when you're ready to protect what you ship.

## Output

A JSON object with a verdict (e.g. 'suspicious' or 'clean'), an array of findings each containing type, location, severity, and description, the number of blocks scanned, a boolean for whether hidden text was found, and the extraction time in milliseconds.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "file": {
   "type": "string",
   "format": "binary",
   "description": "PDF or DOCX file to scan. Upload as multipart/form-data. Maximum file size: 15MB."
  },
  "intent_contract": {
   "type": "object",
   "properties": {
    "trusted": {
     "type": "boolean",
     "description": "Is document from trusted source? Usually false."
    },
    "intent_type": {
     "type": "string",
     "description": "Use \"document_scanning\" for document scans."
    }
   },
   "description": "Intent declaration for drift detection."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "verdict": "suspicious",
  "findings": [
   {
    "type": "hidden_text",
    "location": "annotation_layer",
    "severity": "medium",
    "description": "Hidden instruction found in PDF annotation"
   }
  ],
  "blocks_scanned": 8,
  "hidden_text_found": true,
  "extraction_time_ms": 1847
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/ai-security-guard-document-scanner-64de34a9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from aisecurityguard.io](https://www.zero.xyz/host/aisecurityguard.io/llms.txt)