Tool
GitHub - StackOneHQ/defender: Open source prompt injection protection for Agents calling tools (via MCP, CLI or direct function calling). Detect and defend against prompt injection attacks. 22MB, CPU-only, < 10ms latency.
Publication date not yet evaluated · Added · 2 reports github.com
Page published
Coverage timeline
Why it matters
Defender gives defenders a lightweight, self-hostable guardrail to screen tool-calling and MCP inputs for prompt injection before agents act on untrusted content.
Defender by StackOneHQ is an open-source tool that detects and defends against prompt injection attacks aimed at AI agents that call tools via MCP, CLI, or direct function calling. Described as a 22MB, CPU-only classifier with sub-10ms latency, it is distributed as an npm package with a lightweight model for inline protection.