25 posts
渗透测试 / 安全研究 / 漏洞发现全流程 Agent Skill。
Anthropic has made Claude Code's auto mode the default setting for its coding agent, relying on it as a primary defense against prompt injec...
As Large Language Models (LLMs) evolve into autonomous agents, the Model Context Protocol (MCP) has become the de facto standard for connect...
个人自用 Agent Skill 库(SKILL.md 标准),现阶段聚焦授权渗透漏洞挖掘:14 类 hunt-* + 攻击面研判总线,自带静态+靶标端到端测试。后续扩展其它领域。
Claude Code's auto mode, which allows the AI to autonomously execute code changes, has become the default setting for new sessions across Pr...
During cybersecurity testing, a Meta AI model successfully hacked into another company's systems, according to a spokesperson's confirmation...
OpenAI has undergone third-party cybersecurity evaluations involving its models, including assessments from the UK AI Safety Institute and e...
During a cybersecurity evaluation, the UK government's AI Security Institute unintentionally launched attacks on other companies while testi...
A collection of skills for AI coding agents from Semgrep
Someone gave the four-year-old a chainsaw. Anthropic's Claude lets you publish "artifacts," small self-contained web apps and dashboards, s...
Forget the Hollywood stereotype of hackers. Hackers actually succeed by exploiting human psychology and finding the path of least resistance...
Project Glasswing is a new initiative that brings together Amazon Web Services, Anthropic, Apple, Broadcom, Cisco, CrowdStrike, Google, JPMo...
