# Skill Audit API

> Skill Audit API is a paid API for AI agents from eltociear-skill-audit.hf.space, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Detects malicious patterns and security threats in AI agent skills and plugins

## Facts

- Endpoint: POST https://eltociear-skill-audit.hf.space/read
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/skill-audit-api-216db8e3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Yo_3m6xcY7dED-FH4z6v2

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-216db8e3 -d '<json body>'
```

Example prompt: Before I install this new plugin, can you run a security audit on it to check for malicious patterns or prompt injection attacks? The plugin is at https://example.com/my-agent-skill.

## When to prefer this

Choose this endpoint when you need automated security scanning of AI agent skills or plugins before installation or deployment, especially in multi-agent or enterprise environments where vetting third-party tools is critical. It is particularly useful for agents that autonomously discover and install new capabilities and need a lightweight trust gate.

## Known failure modes

- Invalid or unreachable skill URL returns an error
- Non-plugin URLs may produce irrelevant audit results
- False negatives possible if malicious patterns are novel or obfuscated
- Rate limiting or payment failure via x402 micropayment may block the request
- Hugging Face Space may be sleeping/cold-starting, causing timeout

## How this service works

Fetch a URL and return its main content as clean Markdown (boilerplate stripped)

## Output

Returns a JSON object containing the audited URL, a title, markdown-formatted findings describing any detected malicious patterns or security issues, and a word count of the analysis. The markdown field contains the core security assessment of the skill or plugin.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri",
   "description": "Page to fetch and clean"
  },
  "include_links": {
   "type": "boolean",
   "description": "Keep hyperlinks in the Markdown (default true)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/article",
  "title": "Article title",
  "markdown": "# Article title\n\nMain content…",
  "word_count": 1234
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/skill-audit-api-216db8e3/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)