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.
Model flaws and application flaws in AI agents cause different breaches and need different fixes. Real incidents show where each risk actually lives — and how to test for both.
Attackers smuggle malicious payloads into trusted AI skill repositories via typosquats, staged fetches, and split-file obfuscation — here is exactly how it works.
Most AI model inventories are name-and-owner spreadsheets. Here's the provenance, licensing, CVE, and revalidation fields a real AI model risk registry needs to track.
A precise glossary of agentic AI security terms — prompt injection, tool poisoning, model jailbreaking, excessive agency, and MCP rug pulls — with concrete attack examples.
A practical checklist for scoping MCP server permissions, denying risky defaults, and limiting the blast radius when an AI agent's tool access is exploited.
Agentic codebases build call graphs at runtime, defeating static analysis. Here's why SAST tools miss prompt injection and tool-schema risks—and how Safeguard closes the gap.
OX Security disclosed a DPRK-aligned campaign that abused Hugging Face as a malware host and data-exfiltration backend, using public repos to serve second-stage payloads and private datasets to receive stolen developer secrets.
An AI code detector estimates whether source code was machine-generated. Here is how these tools work, why they misfire, and where security teams should and should not rely on them.
Hacking AI is not science fiction; it is a growing set of concrete techniques that exploit how models learn, process input, and produce output. Here is how to think about defending against them.
Weekly insights on software supply chain security, delivered to your inbox.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.
