Unverified50% confidenceFactExact time
This VM network-layer vulnerability was previously discovered and reported by Johann Rehberger in Claude chat (not Cowork), and Anthropic confirmed it, but it had not been fixed before Cowork launched.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
UnverifiedIn 2023, security researcher Johann Rehberger demonstrated an attack that exploited indirect prompt injection to cause a ChatGPT plugin to leak users' conversation history.64% similarUnverifiedIn 2024, security researcher Johann Rehberger demonstrated an indirect prompt injection attack that successfully hijacked the output of multiple commercial RAG systems by embedding instruction text in public web pages that was invisible to humans but readable by AI60% similarUnverifiedJohann Rehberger展示了通过SharePoint共享文档、Teams消息等多种渠道向Microsoft 365生态注入恶意指令的可能性57% similarUnverifiedThe Hacker News article "Write Like It's 1866: LLMs Relearn Telegraphese" proposes that the Telegraphese writing style becomes valuable again in the LLM era.52% similarUnverifiedResidual connections were proposed by He Kaiming et al. in the 2015 ResNet paper.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033348API
curl https://kongchang.com/api/v1/knowledge/claims/1033348MCP
get_claim(id=1033348)