AI Security
Which OWASP LLM risk to tackle first: chatbot, RAG app or agent
A decision guide to the ten OWASP LLM risks by app type: where to start for a plain chatbot, a RAG assistant and a tool-using agent, with reasons.
Oct 18, 20263 min read
Resources
Supply Chain Security, in plain English.
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.
Filter
Articles
RSS feedAI Security
Who should red team your AI system? NIST's four team types
NIST's Generative AI Profile describes general public, expert, combination and human plus AI red teams. How to pick the right mix for your system.
Oct 18, 20263 min read
AI Security
Who should sit on an AI governance committee?
An AI governance committee needs the right seats: security, legal, privacy, data, engineering and a business owner. Charter, cadence and decision rights.
Oct 18, 20263 min read
AI Security
Why AI agent bills balloon: the hidden costs inside agent loops
Agents resend context on every step, run idle check-ins and spawn helpers. Here are the documented sources of token growth and how to cap each one.
Oct 18, 20263 min read
AI Security
Will AI cause mass cyberattacks by 2027? What the evidence says
The 2026 International AI Safety Report says AI helps attackers at many steps, but fully autonomous end-to-end attacks have not been reported.
Oct 18, 20263 min read
AI Security
XML tags in security prompts: structure, not a security boundary
Tags help a model separate instructions from data but do not stop prompt injection. What they give you, and what still needs checks outside the model.
Oct 18, 20263 min read
AI Security
What is ISO/IEC 27090 and what does it mean for AI security?
ISO/IEC 27090 is guidance on security threats to AI systems. See what it covers, where it stands, and how to prepare. Check ISO for the current edition.
Oct 18, 20265 min read
AI Security
How do you prepare for ISO/IEC 27090 AI security guidance?
Prepare for ISO/IEC 27090 by inventorying AI systems, mapping threats, testing controls and keeping dated evidence. A practical checklist for engineers.
Oct 18, 20265 min read
AI Security
ISO/IEC 27090 vs OWASP LLM Top 10 vs MITRE ATLAS: how they fit
OWASP lists LLM app risks, MITRE ATLAS catalogs attacker behavior, ISO/IEC 27090 is a paid standard on AI threats. Use each for a different job.
Oct 18, 20266 min read
Stay informed
Weekly insights on software supply chain security, delivered to your inbox.
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.