engineering·Independent✓ Verified

Gsh Framework

Open-source hunt playbooks and a policy-driven Sentinel reference framework for detecting runaway AI agents, unauthorized tool calls, behavioral drift, DNS exfiltration, and poisoned MCP tools. MITRE

About

Open-source hunt playbooks and a policy-driven Sentinel reference framework for detecting runaway AI agents, unauthorized tool calls, behavioral drift, DNS exfiltration, and poisoned MCP tools. MITRE ATLAS mapped.

Tags

agentic-ai ai-security behavioral-analysis cybersecurity detection-engineering llm-security github open-source

Pricing

Free

Visit website ↗

Marketplace

Independent