Anthropic、「Claude Code」向けにセキュリティ監査プラグインを無償提供

米Anthropicは5月27日（日本時間）、新しい「Claude ...
InfoWorld

FastAPI-based AI tools exposed to authentication bypass by flaw in Starlette framework

Researchers who found the bug warn that its Moderate rating understates a threat reaching across LLM gateways, MCP servers ...
InfoQ

Designing AI Platforms for Reliability: Tools for Certainty, Agents for Discovery

Aaron Erickson discusses the evolution of AI workflows, shifting from "vibe checking" to building reliable, multi-agent frameworks. He explains how to combine deterministic software guardrails with ...
techtimes

llama.cpp GGUF Parser Flaws: Critical Integer Overflow Enables Arbitrary Reads in Every ...

A security researcher published six vulnerabilities in llama.cpp's model-file parser to the oss-security mailing list on May 15, 2026 — and none of them carry an assigned CVE number, meaning standard ...