惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Hugging Face - Blog
Hugging Face - Blog
宝玉的分享
宝玉的分享
G
Google Developers Blog
T
Tailwind CSS Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
V
V2EX
V
Visual Studio Blog
博客园 - Franky
S
SegmentFault 最新的问题
Jina AI
Jina AI
爱范儿
爱范儿
The Cloudflare Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
D
DataBreaches.Net
C
Check Point Blog
月光博客
月光博客
P
Proofpoint News Feed
T
The Blog of Author Tim Ferriss
罗磊的独立博客
H
Hackread – Cybersecurity News, Data Breaches, AI and More
MongoDB | Blog
MongoDB | Blog
The GitHub Blog
The GitHub Blog
Y
Y Combinator Blog
Martin Fowler
Martin Fowler

Simon Willison's Weblog

Thoughts on GitLab’s workforce reduction A quote from James Shore Your AI Use Is Breaking My Brain TIL: Using LLM in the shebang line of a script Learning on the Shop floor A quote from New York Times Editors’ Note A quote from Andrew Quinn A quote from Luke Curley Release: llm-gemini 0.31 Tool: Big Words Behind the Scenes Hardening Firefox with Claude Mythos Preview Notes on the xAI/Anthropic data center deal Tool: GitHub Repo Stats Live blog: Code w/ Claude 2026 Vibe coding and agentic engineering are getting closer than I’d like Release: datasette-referrer-policy 0.1 Release: datasette-llm 0.1a7 Release: llm-echo 0.5a0 Granite 4.1 3B SVG Pelican Gallery A quote from Andy Masley April 2026 newsletter Research: TRE Python binding — ReDoS robustness demo Tool: Redis Array Playground A quote from Anthropic Sightings iNaturalist Sightings Codex CLI 0.128.0 adds /goal Our evaluation of OpenAI's GPT-5.5 cyber capabilities Quoting Andrew Kelley We need RSS for sharing abundant vibe-coded apps
Microsoft Copilot Cowork Exfiltrates Files
Simon Willison · 2026-05-26 · via Simon Willison's Weblog

26th May 2026 - Link Blog

Microsoft Copilot Cowork Exfiltrates Files (via) The biggest challenge in designing agentic systems continues to be preventing them from enabling attackers to exfiltrate data.

In this case Microsoft Copilot Cowork (yes, that's a real product name) was allowing agents to send emails to the user's own inbox without approval... but those messages were then displayed in a way that could leak data to an attacker via rendered images:

Because these messages can contain external images that trigger network requests to external websites, data can be exfiltrated when a user opens a compromised message sent by the agent.

Since OneDrive can create pre-authenticated download links, a successful prompt injection could cause those links to be leaked, allowing files to be downloaded by the attacker.