AETERNAE AI RESEARCH LLC INDEPENDENT RESEARCH
ÆAETERNAERESEARCH
Sign inRequest access

Attributed metadata history

Up to 100 retained publisher events per page for 534fb50cbdcbc47733b6e02c37afdaac5a7f709fdb983f84f972fe47eb5b88ab. Withdrawals and unavailable references remain attributed to their publishers.

intelligence_src_636032c91a0b4c9a97

observed · 2026-10-12 10:37:04 UTC

A critical vulnerability in LMCache, open-source software that speeds up large language model (LLM) servers such as vLLM, lets an attacker run code on the cache server without logging in, and no fixed version is available. The flaw is in LMCache's multiprocess mode, where the cache runs as a standalone server that LLM workers reach over the ZeroMQ messaging library. A single network

Fingerprint: 955fc7121c940ff1b9b8886e6fc37a227764b5e0bddff1d29a056893f0210837

intelligence_src_636032c91a0b4c9a97

observed · 2026-10-12 10:37:03 UTC

available

Fingerprint: cc58046b4b1d7fb963844e45a69d2195cff987918478e05287925b56bc65734d