Shadow Agents: Red Teaming Multi-Agent LLM Coordination
Shadow agents are stealth behaviors that emerge in multi-agent LLM systems
Month: May 2025
Memory Poisoning in Agentic LLMs
In agentic LLMs, memory is a persistence layer attackers can quietly poison for long-term control
Tool Chaining in Agentic LLMs
Tool chaining in Agentic LLMs isn’t just a feature. It’s a hidden security collapse waiting to happen.
Tenancy in MCP
How shared tool access in multi-tenant MCP servers turns structured prompts into a hidden attack surface
