Lumen Black Lotus Labs

Lumen Black Lotus Labs is a security research team within Lumen Technologies that identifies and publishes vulnerabilities and threat intelligence affecting enterprise networks and software. Their work matters to AI governance because they regularly uncover security flaws in widely used infrastructure, development tools, and cloud services that organizations rely on to build and deploy AI systems safely. When they disclose a vulnerability, compliance teams need to assess whether their AI pipelines use the affected software and determine urgency for patching or mitigation.

1 item

ResearchGlobal2026-10-07

PoeLLM Malware Hits 3,000+ Servers by Hiding Commands Inside AI-Read Poetry

Lumen Black Lotus Labs has documented a malware campaign called Canto Incognito. Attackers compromised more than 3,000 enterprise servers running open-source AI inference tools, including LiteLLM and Ollama, since April 2026. The attackers hid command-and-control instructions inside a poem on GitHub, exploiting the way AI models read external content, to bypass safety guardrails. Compromised servers were used for cryptomining and converted into botnet nodes.

AI infrastructure security adversarial jailbreak cryptojacking prompt injection open-source AI LiteLLM Ollama Lumen Black Lotus Labs