Pass-ta-Key: When Synced Passkeys Trust a Compromised Host
Unit 42’s Pass-ta-key research exposes device-trust and recovery attacks around Google-synced passkeys. Trace the mechanics, detection, and defensive choices.
-
-
Enterprise AI Attack Chains: Prompt Injection, Tool Abuse, Detection
Technical analysis of enterprise AI attack chains: indirect prompt injection, memory poisoning, tool abuse, MCP exposure, and detection.
-
AI Threat Modeling: Trust Boundaries for RAG, Agents, and MCP
Advanced guide to AI threat modeling for RAG, agents, and MCP, with trust boundaries, context provenance, and identity separation.
-
MCP Security: Tools and Permissions in Practice
MCP Security in practice: a safe lab with fictional documents, a mocked local agent, controlled tool exploitation, permissions, schemas, and auditable logs.
