# skill-audit API

> skill-audit API is a paid API for AI agents from eltociear-skill-audit.hf.space, paid per call via x402, $0.03/call, status unknown (last checked 2026-09-14).

Scans an AI agent skill or plugin URL for malicious patterns and returns a risk score with detailed findings

## Facts

- Endpoint: POST https://eltociear-skill-audit.hf.space/audit/url
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/skill-audit-api-1ad08ce8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_psW3KrJ0vvBJjtggBizOe

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 skill-audit-api-1ad08ce8 -d '<json body>'
```

Example prompt: Can you audit this AI agent skill for malicious patterns and tell me the risk level? The skill is at https://example.com/skill.md

## When to prefer this

Use this endpoint when you need to security-audit an AI agent skill, plugin, or capability file before deploying or invoking it — especially when skills come from untrusted third parties. Prefer this over generic URL scanners because it is specifically tuned for AI agent skill/plugin patterns and prompt injection vectors.

## Known failure modes

- Unreachable or invalid URL returns an error or non-200 response
- URL pointing to a non-skill resource may return empty or misleading findings
- Payment failure via x402 results in 402 response before audit is performed
- Timeouts if the target skill URL is slow to respond
- False negatives possible for novel or obfuscated malicious patterns

## How this service works

Fetch a URL and audit its content

## Output

A JSON object containing the original URL, a list of findings (detected malicious patterns), a risk_level string (e.g. 'clean' or severity label), a numeric risk_score, and a total_findings count.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "description": "URL to fetch + audit"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/skill.md",
  "findings": [],
  "risk_level": "clean",
  "risk_score": 0,
  "total_findings": 0
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/skill-audit-api-1ad08ce8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from eltociear-skill-audit.hf.space](https://www.zero.xyz/host/eltociear-skill-audit.hf.space/llms.txt)