AI Security
How to build an AI system inventory in one week
An AI system inventory is the base of AI governance. A one-week plan: scope, sources to scan, fields to record, an owner, and how to keep it current.
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
How much autonomy should an AI SOC agent have?
A decision guide to AI autonomy in security operations: from read-only summaries to supervised response, and why risky actions should wait for a person.
Oct 18, 20263 min read
AI Security
Hidden text in documents: protecting RAG ingestion from it
White-on-white text and other hidden content can carry instructions into a RAG index. How to extract text safely and validate documents before indexing.
Oct 18, 20264 min read
AI Security
Hidden text and invisible characters in LLM inputs: what to strip
Models read text people cannot see, like white-on-white resume text and invisible Unicode. How to extract, normalise and inspect input before the model.
Oct 18, 20263 min read
AI Security
Guard Proxy or Guard SDK: which fits your MCP setup?
Use the SDK when you own the MCP server code, the proxy when you do not. Both enforce the same policy. Components, trade offs and the current SDK status.
Oct 18, 20264 min read
AI Security
Guard proxy errors decoded: 401, 403, 404, 429 and 502 explained
What each Guard proxy response means, from JSON-RPC code -32000 to a bare 401 or 404, and the first thing to check for each.
Oct 18, 20264 min read
AI Security
How Guard policy rules are evaluated: priority and first match wins
Guard checks MCP requests against rules in priority order and applies the first match. What a rule can match, the three actions, and common mistakes.
Oct 18, 20264 min read
AI Security
Guard input and output filters for MCP tool calls, explained
Guard rules can inspect tool inputs before a call and mask or cap tool outputs after. The filter types, what they catch, and where regex filters fall short.
Oct 18, 20264 min read
AI Security
What the Guard audit trail records for every MCP call
Guard logs every MCP request it evaluates, allow, deny or monitor, with scores and rule IDs. What is stored, how long, how to query it, and what is not live.
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.