Source record

Published by arXiv cs.MA (T1 source). The original is at https://arxiv.org/abs/2607.19430.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

The paper demonstrates that individually safe LLMs do not compose into safe multi-agent systems, as inter-agent communication channels are unmonitored attack surfaces. Evaluation of 2,100 traces across 8 attack families showed apparent safety often depends on cloud provider server-side filters. ChannelGuard, a training-free framework using embedding-similarity gates on each inter-agent channel, is proposed and tested.

Identifies a composition gap in multi-agent pipelines and gives a deployable, low-cost defense with measured numbers; relevant to anyone chaining LLM agents.

Cited by

• Safe models do not compose into safe systems