PulseAugur
中
实时 07:48:25
English(EN) MCPhantom: agents chose deprecated MCP servers in 98% of tracked sessions, and no patch is coming

AI代理因过时训练数据而安装易受攻击的MCP服务器

一种名为MCPhantom的安全漏洞已被发现,其中AI编码代理频繁安装已弃用且易受攻击的MCP服务器。Glow Labs的研究人员发现,在跟踪的会话中,AI代理有98%从其训练数据中选择了这些过时的服务器,而不是当前维护的版本。此问题影响了包括Anthropic和OpenAI在内的多家供应商的多个AI模型,由于某些已弃用软件包中存在未修补的远程代码执行漏洞,因此构成了重大风险。 AI

影响 AI代理可能会安装易受攻击的依赖项,需要更好的安全控制和模型训练数据卫生。

排序理由 安全研究论文,详细介绍了AI代理行为中的漏洞。[lever_c_demoted from research: ic=1 ai=1.0]

在 dev.to — MCP tag 阅读 →

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

AI代理因过时训练数据而安装易受攻击的MCP服务器

本文如何被排名

Signal score
62 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
安全研究论文,详细介绍了AI代理行为中的漏洞。[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 — MCP tag TIER_1 English(EN) · Piekwerk ·

    MCPhantom:在跟踪的会话中,代理在98%的情况下选择了已弃用的MCP服务器,且不会有补丁

    <p>On November 2 the Glow Labs research team at Glow Security published a finding it named <a href="https://www.glow.io/blogs/mcphantom-ai-coding-agents-are-installing-vulnerable-deprecated-mcp-servers-from-training-data" rel="noopener noreferrer">MCPhantom</a>: coding agents ask…