Prompt Injection, Hands-On: Attacking My Own Model With Bedrock Guardrails
A disposable Bedrock Guardrails lab with Claude Haiku 4.5 and Converse: 34 prompts, what blocked, what slipped throug...
ai-security
A collection of 3 posts
Building a Rust gRPC AI Security Gateway for LLM Traffic
A Rust gRPC gateway for LLM traffic with policy checks, PII redaction, and metrics for OpenAI and Anthropic.
Claude Code Security: The Smart Way to Integrate AI
Add Claude Code Security to CI/CD as a second net, while keeping deterministic rules as the baseline.