← 返回 Skills 市场

Agent Security Auditor

Name: Agent Security Auditor
Author: aviclaw

作者 aviclaw · GitHub ↗ · v1.0.0

cross-platform ✓ 安全检测通过

574

总下载

当前安装

版本数

在 OpenClaw 中安装

/install agent-security-auditor

功能描述

Audits ERC-8004 agents by analyzing metadata, endpoints, payment configs, and reputation to identify security risks and generate detailed reports.

使用说明 (SKILL.md)

Agent Security Auditor

Scans ERC-8004 agents for security vulnerabilities and generates comprehensive security reports.

Overview

This skill audits ERC-8004 Trustless Agents by querying the Identity Registry and analyzing agent metadata for common security issues. It helps identify potentially malicious or misconfigured agents before interacting with them.

Features

Identity Registry Query: Fetches agent metadata from the ERC-8004 Identity Registry
Metadata Validation: Checks for missing, empty, or suspicious metadata
Endpoint Security: Analyzes service endpoints for red flags
x402 Payment Analysis: Validates payment configuration
Reputation Check: Queries the Reputation Registry for feedback signals
Verification Status: Checks if endpoints are verified via domain control

Usage

# Run the audit script directly with Node.js
node scripts/audit.js \x3Cagent-address> [options]

# Options:
#   --rpc \x3Curl>        RPC endpoint URL (default: https://eth.llamarpc.com)
#   --chain \x3Cid>       Chain ID (default: 1)
#   --output \x3Cfile>    Output file for JSON report
#   --verbose          Enable verbose logging

Example

# Audit an agent on Ethereum mainnet
node scripts/audit.js 0x742d35Cc6634C0532925a3b844Bc9e7595f8bE21

# Audit with custom RPC
node scripts/audit.js 0x742d35Cc6634C0532925a3b844Bc9e7595f8bE21 --rpc https://mainnet.infura.io/v3/YOUR_KEY

# Save report to file
node scripts/audit.js 0x742d35Cc6634C0532925a3b844Bc9e7595f8bE21 --output report.json

What Gets Scanned

Critical Issues

Missing or empty metadata (no name, description)
No registered services/endpoints
Invalid or unreachable agent URI
No agent wallet configured

High Severity Issues

Unverified endpoints (no domain control proof)
Suspicious endpoint patterns (localhost, IP addresses, unusual ports)
No x402 payment support warning
No reputation signals

Medium Severity Issues

No validation registrations
Missing supportedTrust indicators
Inactive agent status

Info

Reputation score summary
Validation count
Service endpoint count

Architecture

agent-security-auditor/
├── SKILL.md           # This file
├── scripts/
│   └── audit.js       # Main audit logic
└── references/
    └── ERC-8004.md    # ERC-8004 specification reference

Dependencies

ethers.js ^6.x - Ethereum blockchain interaction
node-fetch or built-in fetch - HTTP requests for off-chain metadata

Exit Codes

0 - Audit completed successfully
1 - Invalid agent address
2 - Blockchain connection error
3 - Critical error during audit

Notes

Requires internet connection for RPC calls and metadata fetching
Some checks require off-chain metadata fetching which may be slow
Reputation and validation registries are optional deployments

安全使用建议

This skill appears to be what it says (an ERC-8004 agent auditor), but before running it: 1) Review the full scripts/audit.js file yourself (or in a sandbox) to confirm no unexpected behavior. 2) Run the script in an isolated environment (container, VM) if you are concerned about it making network calls to internal/private addresses — the auditor will fetch arbitrary agent URIs and may probe endpoints. 3) Override the default RPC with your preferred provider (--rpc) if you care about privacy or logging (do not supply private keys). 4) Be cautious saving or publishing generated reports if they contain sensitive internal endpoints or metadata. 5) If you need higher assurance, run the tool with network egress controlled and inspect all outgoing requests (or instrument it to log intended requests before they are made).

功能分析

Type: OpenClaw Skill Name: agent-security-auditor Version: 1.0.0 The skill is designed to audit ERC-8004 agents for security vulnerabilities. The `SKILL.md` provides clear, benign instructions for the AI agent. The `scripts/audit.js` code performs network requests (to RPC endpoints and agent metadata URIs) and file system writes (for report generation), which are all legitimate and necessary operations for its stated purpose. The script includes logic to identify suspicious endpoints and configurations, demonstrating an intent to enhance security rather than compromise it. There is no evidence of intentional harmful behavior such as data exfiltration, unauthorized command execution, persistence mechanisms, or obfuscation. The dependencies are standard and reputable.

能力评估

✓ Purpose & Capability

Name/description (ERC-8004 agent auditor) matches the included files and runtime behavior: a Node.js audit script that queries an on‑chain identity registry, fetches off‑chain registration files, inspects endpoints, and reports findings. The declared dependency (ethers) is appropriate for Ethereum RPC interaction.

ℹ Instruction Scope

SKILL.md instructs the agent/user to run scripts/audit.js which performs RPC queries and fetches off‑chain metadata/endpoints. This is within the auditor's purpose, but the script will fetch arbitrary URIs taken from agent registrations (and likely probe service endpoints). That can cause outbound requests to attacker‑controlled or internal/private addresses (SSRF/network scanning risks). The instructions do not explicitly warn about running in a sandbox or the privacy implications of RPC/query traffic.

✓ Install Mechanism

There is no install spec (instruction-only behavior), minimizing on‑disk installation risk. The package.json lists a single dependency (ethers) which is reasonable and traceable on npm. No remote archive downloads or executable installers are used.

✓ Credentials

The skill requests no environment variables, credentials, or config paths. The only implicit external resource is a blockchain RPC endpoint (default: https://eth.llamarpc.com) and network access for fetch calls — these are expected for the stated functionality, but the default RPC is a third‑party service that may log queries and could affect privacy.

✓ Persistence & Privilege

always is false; the skill does not request persistent privileges or modify other skills. It runs as an on‑demand script and does not require enabling itself globally.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install agent-security-auditor
安装完成后，直接呼叫该 Skill 的名称或使用 /agent-security-auditor 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release of Agent Security Auditor. - Scans ERC-8004 agents for security vulnerabilities and generates comprehensive reports. - Fetches agent metadata from the Identity Registry and checks for missing, empty, or suspicious information. - Analyzes service endpoints, x402 payment configuration, and agent reputation. - Provides command-line usage with customizable options for RPC endpoint, chain ID, output file, and verbosity. - Identifies critical, high, and medium severity issues, as well as informational findings. - Returns detailed exit codes for success and error conditions.

元数据

Slug agent-security-auditor

版本 1.0.0

许可证 —

累计安装 2

当前安装数 2

历史版本数 1

常见问题