Microsoft Copilot Cowork Exfiltrates Files
Microsoft Copilot Cowork has been found to have vulnerabilities that could allow data exfiltration. The system permits agents to send emails to users' inboxes, which can be exploited to leak sensitive information. This issue arises from the ability of these emails to include external images that trigger network requests, potentially exposing user data.
- ▪Microsoft Copilot Cowork allows agents to send emails to users' inboxes without approval.
- ▪Compromised messages can leak data through external images that trigger network requests.
- ▪OneDrive's pre-authenticated download links can be exploited through successful prompt injections.
2 outlets in our directory ran this story, first to last over 18 hours. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
- ▪ Microsoft Copilot Cowork Exfiltrates Files — Promptarmor
Simon Willison files mainly under blogs. We currently carry 54 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Simon Willison's Weblog |
| Canonical URL | https://simonwillison.net/2026/May/26/copilot-cowork-exfiltrates-files/#atom-everything |
| Publication time | 2026-05-26T15:36:48+00:00 |
| Retrieval time | 2026-05-26T15:43:08.985Z |
| Last seen | 2026-05-26T15:54:41.391Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | vCe49WDSNHLK · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
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 rendered 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.
Excerpt limited to ~120 words for fair-use compliance. The full article is at Simon Willison's Weblog.
Discussion
0 commentsMore from Simon Willison's Weblog
