Summary
AI-Infra-Guard 4.6 adds an API Checker security-audit module with web-proxy integration, a detector for LLM API poisoning, a v5 Agent-Scan mutation-engine refactor and a DeepSeek Harness prompt-injection assessment. It also tightens YAML rule validation, migrates MCP clients to SDK 2.0 and fixes parser, filename and JSON-serialisation failure modes.
Why it matters
The release gives teams concrete scanners and red-team hooks for attack paths created when coding and infrastructure agents consume APIs, tools and skills.
Related coverage
- GitHub Copilot SDK makes empty-mode skills deny-by-default
- Codex CLI 0.150 makes cross-task coordination and trust controls first-class
- Anthropic updates Claude Code and its TypeScript Agent SDK