agent-scan
View on GitHubSecurity scanner for AI agents, MCP servers and agent skills.
Snyk Agent Scan is a Python CLI that discovers installed AI agent components (agents, MCP servers, and skills) on a machine and scans them for prompt injection, tool poisoning, malware payloads, and secret leakage. It auto-detects configs from Claude, Cursor, Copilot, Windsurf, Gemini CLI, and others.
Use Cases
Scan local MCP server configs for prompt injection and tool poisoningAudit installed agent skills for malware payloads and unsafe credential handlingDiscover agent components (harnesses, MCP servers, skills) across Claude, Cursor, Copilot, Windsurf, Gemini CLI, CodexDetect hardcoded secrets and sensitive data exposure in agent configsRun agent supply chain security checks in CI pipelinesSandboxed evaluation of untrusted third-party MCP configurationsEnterprise-wide agent security risk management with Snyk Evo
Built With
- Language
- Python
- Frameworks
- MCP · pydantic · rich · aiohttp · lark · pytest
Tags
security · supply-chain-security · mcp · prompt-injection · agent-skills · scanner · cli · llm-security · ai-security · static-analysis · secrets-detection · tool-poisoning · vulnerability-scanning · python