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.
An LLM agent with tools is a deputy that holds privileges its users do not. Attackers exploit that gap by tricking the agent into using those privileges on their behalf — here is how to design defenses that hold up.
MCP servers expose three distinct prompt-injection surfaces — resource contents, tool outputs, and sampling requests — and each one needs its own defense layer. Here is how to think about them together.
Tool-poisoning attacks against Model Context Protocol servers hide adversarial instructions inside tool descriptions and silently mutate tool definitions after install. Here is how the attack works and how to defend against it.
Weekly insights on software supply chain security, delivered to your inbox.