Skip to content
The Injection_
LIVE
LIVElast sweep next in--:--:--

[ RSS ][ JSON ][ llms.txt ]

LiteLLM security

An open-source proxy and SDK that puts many model APIs behind one interface.

The Injection has tracked 2 security stories affecting LiteLLM since September 30, 2026 (incident 1, research 1), 1 rated high or critical. The most recent, disclosed October 7, 2026, is "PoeLLM: a cryptomining botnet feeds on exposed LiteLLM servers".

2

Stories

1

High or critical

0

With a CVE

2026-10-07

Latest disclosure

Every LiteLLM story

  1. HIGH

    Incident · Black Lotus Labs

    PoeLLM: a cryptomining botnet feeds on exposed LiteLLM servers

    PoeLLM is a cryptomining botnet that breaks into internet-facing AI services, which Black Lotus Labs says has reached more than 3,400 servers since April 2026. Infected hosts read their next command server from a poem hosted on GitHub.

  2. INFO

    Research · Google Threat Intelligence Group

    Google GTIG: half of 2026 AI flaws hit agent orchestration

    Google Threat Intelligence Group tracked 2,076 vulnerabilities in AI software from January 2025 to August 2026, more than 1,500 of them in 2026, and says agent orchestration frameworks account for half of them.

Questions people ask

Does LiteLLM have known security vulnerabilities?
The Injection has tracked 2 stories about LiteLLM, none of them with a published CVE yet. Several cover attacks or research that apply to it; each story lists what to do.
What is the latest LiteLLM security issue?
The most recent story is "PoeLLM: a cryptomining botnet feeds on exposed LiteLLM servers" (high severity), disclosed October 7, 2026 by Black Lotus Labs. PoeLLM is a cryptomining botnet that breaks into internet-facing AI services, which Black Lotus Labs says has reached more than 3,400 servers since April 2026. Infected hosts read their next command server from a poem hosted on GitHub.
Which attack techniques have been used against LiteLLM?
Stories about LiteLLM on The Injection most often involve ai threat intelligence, remote code execution (rce), mcp (model context protocol). Each technique has a glossary entry with a definition and every related story.