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.
Bedrock Guardrails now span prompt filtering, contextual grounding checks, and tool-use policies. We trace how they fit into a supply chain threat model for production agents.
The MCP client surface is often overlooked. We examine trust boundaries, schema handling, credential storage, and safe defaults for the agent side of the protocol.
Multi-agent systems inherit every trust problem of single-agent systems and add a few more. Here is how the threat model actually shifts.
If your agent can execute code, something it reads from the internet can execute code. Pick your sandbox before the agent picks one for you.
Prompt injection stopped being an LLM curiosity the moment agents started committing code. It is now a software supply chain risk and should be modeled as one.
Most MCP threat models confuse protocol risk with deployment risk. Here is what the real attack surface looks like after a year of production incidents.
Claude Code MCP servers run with the privileges of the developer who invoked them. That makes deployment posture the entire security model.
Weekly insights on software supply chain security, delivered to your inbox.