Skip to content

Add AgentShield — security scanner for AI agent skills & MCP servers#1767

Open
elliotllliu wants to merge 1 commit intoanalysis-tools-dev:masterfrom
elliotllliu:add-agent-shield
Open

Add AgentShield — security scanner for AI agent skills & MCP servers#1767
elliotllliu wants to merge 1 commit intoanalysis-tools-dev:masterfrom
elliotllliu:add-agent-shield

Conversation

@elliotllliu
Copy link

Adds AgentShield to the Security/SAST section.

AgentShield is an open-source security scanner purpose-built for the AI agent ecosystem:

  • 31 detection rules covering prompt injection, data exfiltration, backdoors, tool poisoning, and cross-file attack chains
  • MCP runtime proxy for real-time interception
  • Python AST taint tracking (not regex-based)
  • Multi-language prompt injection detection (8 languages)
  • MIT license, actively maintained

📦 npm: https://www.npmjs.com/package/@elliotllliu/agent-shield
🔗 GitHub: https://github.com/elliotllliu/agent-shield

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant