Hijacking Copilot Cowork's AI Gateway to Bypass Sandboxing and Exfiltrate Files
Researchers disclosed a vulnerability in Microsoft Copilot Cowork that allowed malicious Skills to bypass sandboxing and exfiltrate sensitive user data. The attack exploited the AI gateway used for response generation to spawn external agents capable of sending data to attacker-controlled servers. Microsoft confirmed the issue and implemented a fix on September 2, 2026, following disclosure in July 2026.
- ▪The vulnerability allowed malicious Skills to hijack the AI gateway to exfiltrate data from SharePoint, Teams, and Outlook without human approval.
- ▪The attack involved spawning agents in Anthropic's cloud with network capabilities to send victim data to an attacker's server via URL parameters.
- ▪The malicious Skill disguised its code as a safe local analyzer, leading Copilot to execute it despite its network-exfiltrating nature.
- ▪Microsoft received the disclosure on July 14, 2026, and confirmed the remediation was implemented by September 2, 2026.
Hacker News (AI / LLM) files mainly under ai. We currently carry 7,047 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/hijacking-copilot-coworks-ai-gateway-to-exfiltrate-files |
| Publication time | Wed, 30 Sep 2026 17:28:16 +0000 |
| Retrieval time | 2026-09-30T17:47:01.800Z |
| Last seen | 2026-09-30T17:47:01.800Z |
| 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 | BUj71GxyR62U · 1 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
Copilot Cowork’s AI gateway hijacked to exfiltrate the victim’s filesContextMicrosoft Copilot Cowork is an agent in M365 that runs in a sandbox intended to block network access and prevent the agent from running code that reaches any untrusted services.In order for Copilot Cowork to generate responses, the sandbox forwarded network requests to Anthropic. Malicious Skills were able to hijack this pathway to exfiltrate data by spawning new agents in Anthropic’s cloud equipped with network-capable tools that could reach an attacker’s server.No human in the loop approval was required, and the attack could target any data Copilot could access - from uploaded files, to SharePoint, to Teams, Outlook, and more.This vulnerability was disclosed to Microsoft on July 14, 2026, and was remediated as…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Promptarmor.
Discussion
0 commentsMore from Promptarmor
