All posts
Topic
Agent Security
2 articles on agent security.
MCP Server Governance: The Controls That Keep AI Tool Access Safe
The Model Context Protocol lets AI agents call external tools and data through MCP servers. The governance controls that prevent an over-privileged or malicious MCP server becoming your next incident.
September 26, 2026
When Correct Security Controls Still Leak: The CONTINUITY Paper on Composable Agent Security
A plain-English CISO read of CONTINUITY (arXiv:2609.05269): why individually correct LLM-agent security controls fail to compose, the "security-context discontinuity" failure mode, how CONTINUITY carries authenticated context across every boundary, and its result — zero harmful effects across 2,560 attack instances while completing all benign tasks and escalating every ambiguous case.
September 7, 2026