Microsoft Copilot Cowork Exfiltrates Files
Microsoft Copilot Cowork has been found to be vulnerable to file exfiltration attacks due to insecure automatic action approvals. Attackers can exploit this vulnerability through indirect prompt injection, allowing them to exfiltrate files from Microsoft 365. The issue arises from the lack of human approval for sending emails and Teams messages to the active user, which can trigger malicious actions.
- ▪Copilot Cowork can exfiltrate files by sending compromised messages that contain pre-authenticated download links.
- ▪The vulnerability allows attackers to manipulate the system without requiring human approval for sensitive actions.
- ▪Users are at risk due to the design of the system, which grants agents access to multiple systems within the Microsoft ecosystem.
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 — Simon Willison's Weblog
Hacker News (Newest) files mainly under programming. We currently carry 5,306 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 | Promptarmor |
| Canonical URL | https://www.promptarmor.com/resources/microsoft-copilot-cowork-exfiltrates-files |
| Publication time | Mon, 25 May 2026 21:45:57 +0000 |
| Retrieval time | 2026-05-25T22:07:40.571Z |
| Last seen | 2026-05-25T22:07:40.571Z |
| 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
Threat IntelligenceTable of ContentMicrosoft Copilot Cowork Exfiltrates FilesMicrosoft Copilot Cowork is vulnerable to file exfiltration attacks via indirect prompt injection as a result of insecure automatic action approvals for sending Emails and Teams messages..framer-text { scroll-margin-top: 80px; }This attack achieved a high success rate against state-of-the-art models, including Claude Opus 4.7.OverviewCopilot Cowork is a Frontier feature available now in Microsoft 365. It operates with the users’ Microsoft permissions and can use Microsoft Graph to read and operate on data in one’s Microsoft tenant.In this article, we demonstrate that through an indirect prompt injection in a poisoned skill, attackers can exfiltrate files from M365.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Promptarmor.
Discussion
0 commentsMore from Promptarmor
