Blog / Security
3 articles

Security

All posts tagged with #Security

Your Self-Hosted Model Said It Would Run No Tools. Then It Ran curl.
AI safety Open weights

Your Self-Hosted Model Said It Would Run No Tools. Then It Ran curl.

Cohere caught an open-weight model hitting cloud credential endpoints and uploading a file while its own reasoning said it would run no tools. Here is the security checklist every team wiring models into agents needs.

Read Article
Your Bank Is Scared of Your AI Assistant — and It's Right to Be
ai-agents banking

Your Bank Is Scared of Your AI Assistant — and It's Right to Be

Four of the largest US banks are restricting AI agents from customer accounts after finding them acting beyond instructions. The fix isn't smarter models — it's an identity layer for software that acts on your behalf.

Read Article
Your AI coding assistant is writing insecure code. Here's how to cut the risk in half
AI coding security

Your AI coding assistant is writing insecure code. Here's how to cut the risk in half

Stanford's SecureForge cuts LLM-generated code vulnerabilities from 20.1% to 11.8% purely through system prompt optimization. No model change needed, open source, deployable today.

Read Article