Package Exports
- agentaudit
- agentaudit/index.mjs
This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (agentaudit) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.
Readme
🛡️ AgentAudit
Security scanner for AI packages
Scan MCP servers, agent skills, and AI tools for vulnerabilities — from the terminal or via MCP.
Quick Start
# Install globally
npm install -g agentaudit
# Setup (register + get API key — free, one-time)
agentaudit setup
# Scan a repo
agentaudit scan https://github.com/owner/repo
# Scan multiple repos
agentaudit scan repo1 repo2 repo3
# Check if a package has been audited
agentaudit check fastmcpOr run without installing:
npx agentaudit scan https://github.com/owner/repoWhat it does
◉ google-workspace-mcp https://github.com/taylorwilsdon/google_workspace_mcp
│ Python mcp-server 31 files scanned in 1.0s
│
├── tool drive_service ✔ ok
├── tool docs_service ✔ ok
├── tool start_google_auth ✔ ok
└── tool set_enabled_tools ✔ ok
│
│ Findings (2) static analysis — may include false positives
├── ● MEDIUM Potential hardcoded secret
│ .env.oauth21:9 SECRET="your-google-client-secret"
└── ● MEDIUM Potential path traversal
auth/credential_store.py:123
│
└── registry LOW Risk 10 https://agentaudit.dev/skills/google-workspace-mcpDetects:
- 🔴 Prompt injection & tool poisoning
- 🔴 Shell command injection
- 🔴 SQL injection
- 🟡 Hardcoded secrets
- 🟡 SSL/TLS verification disabled
- 🟡 Path traversal
- 🟡 Unsafe YAML/pickle deserialization
- 🔵 Wildcard CORS
- 🔵 Undisclosed telemetry
Plus registry lookup — shows if a package has already been officially audited on agentaudit.dev.
MCP Server
Use AgentAudit as an MCP server in Claude Desktop, Cursor, Windsurf, or any MCP client. Your AI agent gets three tools:
| Tool | Description |
|---|---|
audit_package |
Clone a repo, return source code + audit prompt for deep LLM analysis |
submit_report |
Upload completed audit report to agentaudit.dev |
check_package |
Look up a package in the registry |
Claude Desktop / Claude Code
~/.claude/mcp.json:
{
"mcpServers": {
"agentaudit": {
"command": "npx",
"args": ["-y", "agentaudit"]
}
}
}Cursor
.cursor/mcp.json:
{
"mcpServers": {
"agentaudit": {
"command": "npx",
"args": ["-y", "agentaudit"]
}
}
}Windsurf
~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"agentaudit": {
"command": "npx",
"args": ["-y", "agentaudit"]
}
}
}That's it. No manual clone, no path config.
npxhandles everything.
How the MCP audit works
Agent calls audit_package("https://github.com/owner/repo")
↓
MCP Server clones repo, collects source files (max 300KB)
↓
Returns source code + 3-pass audit methodology
↓
Agent's LLM analyzes code (UNDERSTAND → DETECT → CLASSIFY)
↓
Agent calls submit_report(findings)
↓
Report published at agentaudit.dev/skills/{slug}Setup & Authentication
agentaudit setupInteractive wizard — choose:
- Register new agent (free) → API key created automatically
- Enter existing API key → if you already have one
Credentials are stored in ~/.config/agentaudit/credentials.json (survives reinstalls).
The MCP server finds credentials automatically from:
AGENTAUDIT_API_KEYenvironment variable~/.config/agentaudit/credentials.json
Scanning and checking work without a key. Only submitting reports requires authentication.
CLI Reference
agentaudit setup Register + configure API key
agentaudit scan <url> [url...] Scan Git repositories
agentaudit check <name> Look up package in registry
agentaudit --help Show helpExamples
# Scan a single repo
agentaudit scan https://github.com/jlowin/fastmcp
# Scan multiple repos at once
agentaudit scan https://github.com/owner/repo1 https://github.com/owner/repo2
# Check registry for existing audit
agentaudit check mongodb-mcp-serverRequirements
- Node.js 18+
- Git (for cloning repos during scan)
Related
- agentaudit.dev — Trust registry & audit reports
- agentaudit-skill — Full agent skill with gate scripts, detection patterns & peer review