AI Security
Data Exfiltration via LLM Agents in 2026
Tool-using agents have become a viable exfiltration channel. The patterns showing up in incident reports, and the controls that contain them.
May 6, 20266 min read
Deep dives, practical guides, and incident analyses from engineers who build Safeguard. No fluff, no vendor FUD — just what you need to ship secure software.
Tool-using agents have become a viable exfiltration channel. The patterns showing up in incident reports, and the controls that contain them.
Tool-using agents are now in production at most large organizations. The security baseline that should be table stakes, and what teams are still missing.
A senior engineer's take on the confused deputy problem in AI agent tool use, why it keeps reappearing in 2026, and the architectural patterns that actually fix it.
Persistent memory makes AI agents more useful and more dangerous. A security engineer's walkthrough of how agent memory gets poisoned, exfiltrated, and weaponised, with concrete 2025 examples.
Weekly insights on software supply chain security, delivered to your inbox.