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.
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.
A senior engineer's breakdown of indirect prompt injection in RAG pipelines, how real attacks land through retrieved content, and what actually reduces exposure.
Prompt injection remains the LLM01 entry on the OWASP LLM Top 10 for a reason. A pragmatic look at the defense architectures that hold up in production this year.
Retrieval-augmented generation is the most common LLM deployment pattern in the enterprise and the most commonly poisoned. A senior security engineer's playbook for defences that hold up in production.
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.