File contents 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 <agent-address> [options]
# Options:
# --rpc <url> RPC endpoint URL (default: https://eth.llamarpc.com)
# --chain <id> Chain ID (default: 1)
# --output <file> 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
1 --- 2 name: agent-security-auditor 3 description: Agent Security Auditor 4 --- 5 # Agent Security Auditor 6 7 Scans ERC-8004 agents for security vulnerabilities and generates comprehensive security reports. 8 9 ## Overview 10 11 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. 12 13 ## Features 14 15 - **Identity Registry Query**: Fetches agent metadata from the ERC-8004 Identity Registry 16 - **Metadata Validation**: Checks for missing, empty, or suspicious metadata 17 - **Endpoint Security**: Analyzes service endpoints for red flags 18 - **x402 Payment Analysis**: Validates payment configuration 19 - **Reputation Check**: Queries the Reputation Registry for feedback signals 20 - **Verification Status**: Checks if endpoints are verified via domain control 21 22 ## Usage 23 24 ```bash 25 # Run the audit script directly with Node.js 26 node scripts/audit.js <agent-address> [options] 27 28 # Options: 29 # --rpc <url> RPC endpoint URL (default: https://eth.llamarpc.com) 30 # --chain <id> Chain ID (default: 1) 31 # --output <file> Output file for JSON report 32 # --verbose Enable verbose logging 33 ``` 34 35 ## Example 36 37 ```bash 38 # Audit an agent on Ethereum mainnet 39 node scripts/audit.js 0x742d35Cc6634C0532925a3b844Bc9e7595f8bE21 40 41 # Audit with custom RPC 42 node scripts/audit.js 0x742d35Cc6634C0532925a3b844Bc9e7595f8bE21 --rpc https://mainnet.infura.io/v3/YOUR_KEY 43 44 # Save report to file 45 node scripts/audit.js 0x742d35Cc6634C0532925a3b844Bc9e7595f8bE21 --output report.json 46 ``` 47 48 ## What Gets Scanned 49 50 ### Critical Issues 51 - Missing or empty metadata (no name, description) 52 - No registered services/endpoints 53 - Invalid or unreachable agent URI 54 - No agent wallet configured 55 56 ### High Severity Issues 57 - Unverified endpoints (no domain control proof) 58 - Suspicious endpoint patterns (localhost, IP addresses, unusual ports) 59 - No x402 payment support warning 60 - No reputation signals 61 62 ### Medium Severity Issues 63 - No validation registrations 64 - Missing supportedTrust indicators 65 - Inactive agent status 66 67 ### Info 68 - Reputation score summary 69 - Validation count 70 - Service endpoint count 71 72 ## Architecture 73 74 ``` 75 agent-security-auditor/ 76 ├── SKILL.md # This file 77 ├── scripts/ 78 │ └── audit.js # Main audit logic 79 └── references/ 80 └── ERC-8004.md # ERC-8004 specification reference 81 ``` 82 83 ## Dependencies 84 85 - ethers.js ^6.x - Ethereum blockchain interaction 86 - node-fetch or built-in fetch - HTTP requests for off-chain metadata 87 88 ## Exit Codes 89 90 - `0` - Audit completed successfully 91 - `1` - Invalid agent address 92 - `2` - Blockchain connection error 93 - `3` - Critical error during audit 94 95 ## Notes 96 97 - Requires internet connection for RPC calls and metadata fetching 98 - Some checks require off-chain metadata fetching which may be slow 99 - Reputation and validation registries are optional deployments
aviclaw/agent-security-auditor/tree/main/ commit f7ecf6094f
Frequently asked questions How do I install the Agent Security Auditor skill? Run npx skillmds@latest add aviclaw/agent-security-auditor in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
What does the Agent Security Auditor skill do? Agent Security Auditor It is listed under AI & ML on SkillMD.
Is Agent Security Auditor safe to use? This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
Which AI agents work with Agent Security Auditor? This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Is Agent Security Auditor free to use? Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Who published Agent Security Auditor? aviclaw (@aviclaw) published this skill. Their other Agent Skills are listed on their SkillMD profile.