AI Security
How to scope an AI red team exercise in three phases
How to scope an AI red team exercise in three phases, plan, execute, then assess and report, following the MITRE ATLAS AI Red Team mitigation.
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
What to scan before you index: a checklist for private search
Secrets, personal data, hidden text and unreviewed sources can all end up in your search index. A pre-indexing checklist you can run as a script.
Oct 18, 20263 min read
AI Security
How to sandbox a local MCP server before you run it
A local MCP server runs with your privileges. Read the exact startup command, restrict files and network, and prefer stdio. A practical sandboxing guide.
Oct 18, 20263 min read
AI Security
Samsung ChatGPT source code leak: what was reported and what was not
In 2023 Samsung restricted generative AI after staff uploaded source code to ChatGPT. What the memo said, what remains unknown, and the lessons.
Oct 18, 20263 min read
AI Security
What safetensors protects against, and what it does not
Safetensors stores tensors without executable code, which removes the pickle risk. It does not prove a model is trustworthy. Here is the difference.
Oct 18, 20263 min read
AI Security
Run agent actions as the user, not a shared service account
OWASP advises running agent actions in the individual user's context, not a generic high-privilege account. Here is why and how to build it.
Oct 18, 20263 min read
AI Security
RLAIF vs RLHF: training with AI feedback instead of human labels
RLHF uses human preference labels; RLAIF uses an LLM to produce them. What a 2023 study reported, what it costs you, and the risks of AI judges.
Oct 18, 20263 min read
AI Security
Restricting agent tool calls after retrieving untrusted data
When should an AI agent pause for approval after reading untrusted text? A decision guide built on the ATLAS tool invocation and approval mitigations.
Oct 18, 20263 min read
AI Security
Replit agent deleted a production database: what was reported
What The Register reported about the July 2025 SaaStr and Replit database deletion incident, what remains unconfirmed, and what teams should take from 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.