Suggesting AgentShield for inclusion.
Open-source security scanner for AI agent skills, MCP servers, and plugins:
- 30 detection rules covering data exfiltration, backdoors, prompt injection, tool poisoning, supply chain attacks
- AST taint tracking, cross-file analysis, kill chain detection
- Multi-language prompt injection (8 languages)
npx @elliotllliu/agent-shield scan ./path/ — zero install, offline, MIT
📦 https://www.npmjs.com/package/@elliotllliu/agent-shield
Suggesting AgentShield for inclusion.
Open-source security scanner for AI agent skills, MCP servers, and plugins:
npx @elliotllliu/agent-shield scan ./path/— zero install, offline, MIT📦 https://www.npmjs.com/package/@elliotllliu/agent-shield