Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
Factual evidence
What the source reports
Researchers introduced Agent Mosaic, demonstrating how LLM agents aggregate non-sensitive documents to disclose confidential conclusions.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 23 October 2026
- Collected by OneBench
- 24 Oct 2026, 03:01 UK
Stored source excerpt
arXiv:2610.30418v1 Announce Type: cross Abstract: Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled from them. This mosaic…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.
OneBench interpretation
Institutional assessment
So what
LLM agents aggregating non-sensitive internal documents can bypass standard data loss controls by inferring restricted information via the mosaic effect.
Do what
Review agent access permissions and data aggregation risks with the team responsible for information security and model governance.