PulseAugur
中
实时 10:30:24
English(EN) Markdown Is the New Executable: What the AGENTS.md-in-Downloads Attack Teaches Us About Coding Agent Security

研究表明,编码代理易受恶意 Markdown 文件攻击

安全研究公司 Forever Security 发现了一个编码代理漏洞,其中嵌入在 Markdown 文件中的恶意指令可以被执行。这些文件通常保存在用户的下载文件夹中,会欺骗 OpenAI Codex 和 Claude Code 等代理运行有害命令,例如安装恶意软件或窃取敏感数据。该攻击利用了代理对本地指令文件的信任,并绕过了操作系统对执行下载内容的标准保护。 AI

影响 凸显了 AI 编码代理的关键安全漏洞,需要新的防御措施来防范恶意指令文件。

排序理由 安全研究,详细介绍了针对 AI 编码代理的新攻击向量。[lever_c_demoted from research: ic=1 ai=1.0]

在 dev.to — LLM tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

研究表明,编码代理易受恶意 Markdown 文件攻击

本文如何被排名

Signal score
44 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
安全研究,详细介绍了针对 AI 编码代理的新攻击向量。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
safety, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. dev.to — LLM tag TIER_1 English(EN) · M.T.Ramkrushna ·

    Markdown 成为新的可执行文件:AGENTS.md-in-Downloads 攻击对我们了解编码代理安全有何启示

    <p>On October 22, 2026, Forever Security published research with a title that every team running coding agents should take literally: <strong>"Markdown Is the New Executable."</strong> Their software had stopped a coding agent on a real customer's machine from installing <code>fu…