5 results for “topic:tool-poisoning”
Real-time security layer protecting AI Agents from Confused Deputy attacks, malicious MCP payloads, and Indirect Prompt Injection.
Local static scanner for MCP setup, config, prompts, and workflow trust.
Live PoC: MCP rug pull attack that steals AI agent credentials mid-session and how to block it in 3 lines of code.
Supply chain security for MCP — pin, hash, detect drift in your AI tool chains
Security scanner for AI agent tools — detect tool poisoning, data exfiltration, and supply chain attacks in MCP servers and agent skills