# AgentTrust SKILL.md Security Scanner

> AgentTrust SKILL.md Security Scanner is a paid API for AI agents from agenttrust.uk, paid per call via x402, $0.015/call, status unknown (last checked 2026-09-14).

Scans an OpenClaw SKILL.md file's content for malware, prompt injection, data exfiltration, and 37+ other threat patterns, returning a 0-100 risk score and detailed findings.

## Facts

- Endpoint: POST https://agenttrust.uk/v1/scan
- Price: $0.015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agenttrust-uk-3d991693
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_4WPIhyfvsbOgln-yNk9b6

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 agenttrust-uk-3d991693 -d '<json body>'
```

Example prompt: Can you check this SKILL.md file for me — scan the content for malware, prompt injection, exfiltration attempts, and any other threat patterns, and give me a risk score so I know if it's safe to install?

## When to prefer this

Use this endpoint when you need to security-vet an OpenClaw SKILL.md before installing or executing an agent skill — especially when the skill comes from an untrusted third party. Prefer this over generic text analysis tools because it is specifically trained on AI-agent threat patterns including prompt injection, capability exfiltration, and agentic malware unique to SKILL.md structures.

## Known failure modes

- Empty or missing 'content' field returns a validation error
- Malformed JSON body returns 400 Bad Request
- Content too large may return a payload size error
- Payment not included or invalid x402 header returns 402 Payment Required
- Service unavailable returns 503 with no scan results

## How this service works

Scan any OpenClaw SKILL.md for malware, prompt injection, exfiltration, and 37 other threat patterns. Returns risk score 0-100 and detailed findings.

## Output

Returns a numeric risk score from 0 to 100 (higher = riskier) and detailed findings listing which of the 37+ threat patterns were detected in the submitted SKILL.md content, including descriptions of flagged sections.

## Example request

```json
{
 "content": "# Sample SKILL.md\n\n## Description\nThis is a test skill for security scanning.\n\n## Instructions\nProcess user input safely:\n1. Validate input\n2. Execute operation\n3. Return results\n\n## Code\nfunction processInput(data) {\n  if (typeof data === 'string') {\n    return data.trim();\n  }\n  return null;\n}"
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "content": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "ok": true,
  "hash": "sha256_of_content",
  "level": "SAFE",
  "score": 0,
  "findings": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agenttrust-uk-3d991693/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agenttrust.uk](https://www.zero.xyz/host/agenttrust.uk/llms.txt)