sunilgentyala/gsh-framework

Improve CLI error messages in gsh-sentinel-deploy.py about 2 hours ago

enhancement good first issue

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Create Hunt-006: Agent Memory Poisoning about 2 hours ago

help wanted playbook

sunilgentyala/gsh-framework

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Add SARIF report output about 2 hours ago

enhancement help wanted

sunilgentyala/gsh-framework

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Add a LangChain callback adapter about 2 hours ago

help wanted adapter

sunilgentyala/gsh-framework

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Add Windows Event Log output adapter about 2 hours ago

help wanted adapter

sunilgentyala/gsh-framework

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Add Elastic bulk-output adapter about 2 hours ago

help wanted adapter

sunilgentyala/gsh-framework

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Add Docker Compose demo (mock MCP server + Hunt-005 walkthrough) about 2 hours ago

enhancement help wanted

sunilgentyala/gsh-framework

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Add Splunk HEC output adapter about 2 hours ago

help wanted adapter

sunilgentyala/gsh-framework

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Add architecture diagram to README about 2 hours ago

documentation good first issue

sunilgentyala/gsh-framework

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Add sample benign + rogue MCP telemetry to examples/ about 2 hours ago

documentation good first issue

sunilgentyala/gsh-framework

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Add unit tests for parse_duration() about 2 hours ago

good first issue

sunilgentyala/gsh-framework

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Add JSON Schema validation for Sentinel policy YAML about 2 hours ago

enhancement good first issue

sunilgentyala/gsh-framework

4

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.

Python

#agentic-ai#ai-security#behavioral-analysis#cybersecurity#detection-engineering#llm-security#mcp-security#mitre-atlas#multi-agent-systems#nist-csf#post-quantum#threat-hunting#zero-trust

Open Issues Need Help