8 projects
agenthive-sim
Multi-agent attack simulation framework for AI systems
datashield-ai
Data sanitization with privacy preservation for AI training
mcp-taxonomy
Canonical taxonomy and cross-project adapters for the MCP security ecosystem
mcpwn-core
Offensive security testing framework for MCP (Model Context Protocol) protocols
reverse-abliterate
Detect and reverse model abliteration; harden LLMs against safety removal
palisade-scanner
Scan web content for prompt injection, hidden instructions, and adversarial content targeting AI agents
mcpscope
Unified security dashboard for MCP/A2A scanner results
mcpguard-proxy
Runtime security proxy for MCP (Model Context Protocol) and A2A (Agent-to-Agent)
