AI Security
AI coding assistant security evaluation: questions for the vendor
What to ask an AI coding assistant vendor before rollout: data handling, retention, training use, admin controls, agent mode and incident response.
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
AI chat privacy myths vs facts for families
Seven common beliefs about AI chat privacy, checked against Anthropic and Google documentation: delete, incognito, links, voice, location and human review.
Oct 18, 20263 min read
AI Security
AI agent security tool categories: which one do you actually need?
AI agent security tools fall into a few categories: discovery, identity, guardrails, testing and observability. How to tell which problem you have first.
Oct 18, 20263 min read
AI Security
What should an AI agent kill switch cover? A buyer's checklist
An AI agent kill switch should stop actions, revoke credentials, halt queued work and keep a record. Use this checklist to test whether yours really works.
Oct 18, 20263 min read
AI Security
What questions should an AI agent intake form ask before approval?
An AI agent intake form should ask ten questions: purpose, owner, tools, data, credentials, approvals, logging, failure, stop plan and review date.
Oct 18, 20264 min read
AI Security
AI agent identity: a buyer's checklist for evaluating products
What to check when a product claims to manage AI agent identity: unique identities, scoped credentials, expiry, delegation, revocation and audit evidence.
Oct 18, 20263 min read
AI Security
The Agents Rule of Two: pick two of three risky properties
Meta's Agents Rule of Two says an agent session should hold no more than two of three properties: untrusted input, sensitive access, or the power to act.
Oct 18, 20264 min read
AI Security
An AI agent registry entry: the fields worth recording
A registry of agents only helps if each entry answers the questions you will ask in an incident. Fields to capture, with examples and common gaps.
Oct 18, 20263 min read
AI Security
Agent pilot to production: seven gates to pass first
A pilot agent run by one enthusiastic team is not ready for production. Seven gates covering owner, access, testing, logging, rollback and review.
Oct 18, 20263 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.