一、引言：Anthropic Agent Skills的发展史起源：时间拨回2025年10月16日，Anthropic在 Claude 3.7 Sonnet / Opus 中正式推出 Claude Skills ...

Hackers hijacked the npm account of the Axios package, a JavaScript HTTP client with 100M+ weekly downloads, to deliver ...

An attacker compromised the npm account of a lead Axios maintainer on March 30, and used it to publish two malicious versions ...

报告日期：2026-02-28 关键词： Agent Skills, MCP, OpenClaw, A2A, Agentic AI, 模块化架构一、谁提出了从 Agent 到 Skills 的转变？1.1 起源：Anthropic ...

Overview: Poor data validation, leakage, and weak preprocessing pipelines cause most XGBoost and LightGBM model failures in production.Default hyperparameters, ...

Malicious telnyx 4.87.1/4.87.2 on PyPI used audio steganography March 27, 2026, enabling cross-platform credential theft.

Blender Live Link connects Blender and Unreal for one-click sending and live sync, plus material baking and UV handling.

Overview Recently, NSFOCUS Technology CERT detected that the GitHub community disclosed that there was a credential stealing program in the new version of LiteLLM. Analysis confirmed that it had ...

Malicious LiteLLM 1.82.7–1.82.8 via Trivy compromise deploys backdoor and steals credentials, enabling Kubernetes-wide ...