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
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 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
AI Security
Agent credentials: issue, scope, expire and revoke
A lifecycle for the credentials an AI agent holds: one identity per agent, narrow scopes, short lifetimes, monitored use and a revoke path you have tested.
Oct 18, 20263 min read
AI Security
Which AI tools belong in your AI inventory? A decision guide
Does an AI feature inside a vendor app belong in your AI inventory? A decision guide for in-house models, APIs, embedded features and agents.
Oct 18, 20263 min read
AI Security
Which AI agent tool calls need human approval?
A decision guide for human-in-the-loop approval on agent tool calls, based on the MCP spec and OWASP guidance: irreversible, external and costly actions.
Oct 18, 20263 min read
AI Security
Which AI agent actions should ask for approval first?
A simple way to sort agent tool calls into allow, ask and block, using impact, reversibility and reach, with OWASP and MCP guidance behind it.
Oct 18, 20264 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.