Not classified

PoeLLM botnet targets 3,400+ exposed LiteLLM/Ollama servers for mining

PoeLLM malware exploits vulnerable internet-facing AI/LLM deployments (LiteLLM, Ollama, Gotenberg, Gitea, possibly Ivanti Sentry CVE-2026-10520). Derives C2 from keywords in poem 'On the Nature of…

What happened

PoeLLM malware exploits vulnerable internet-facing AI/LLM deployments (LiteLLM, Ollama, Gotenberg, Gitea, possibly Ivanti Sentry CVE-2026-10520). Derives C2 from keywords in poem 'On the Nature of Connection' hosted in GitHub repo ejejejdfbbebe/nodejs.org fork (dash.css file). Malware parses poem to extract 4 words/phrases via pattern matching ('In the silent hum of X,', 'each pulse of X threading', 'Beyond the wall of X,', 'the X servers'), converts words to numbers via hardcoded dictionary, combines to form IPv4 C2 address. Deploys XMRig and Iron crypto miners connecting to Kryptex (5.180.174.162). Converts victims into HTTP/S scanners and exploit servers for expansion. Poem updated 11 times since Apr 13, 2026 to rotate C2. Italian-speaking actor. 3,400+ victims, peak 800 active/day, predominantly US/Western Europe.

Malware targets exposed AI/LLM services (LiteLLM, Ollama) for cryptocurrency mining; uses GitHub-hosted poem to derive C2 address; turns victims into scanners

Read the original source

How it happened

Select a stage to explore its defenses
Select a stage · Drag to explore · + / − to zoom · Dashed edges are loopsSelect a stage · Arrows show reported connectionsReported sequence
Read the flow as text & sources

A catalog reconstruction of the supplied source account. Unknown steps remain explicit; an edge describes the reported relationship between steps.

  1. 01 · Exploit vulnerable AI/LLM services

    Target publicly exposed LiteLLM, Ollama, Gotenberg, Gitea, possibly Ivanti Sentry CVE-2026-10520; Gotenberg docs explicitly warn not to expose to internet

    Source for step 1
  2. 02 · GitHub poem-derived C2

    Malware queries GitHub repo ejejejdfbbebe/nodejs.org fork for dash.css; parses poem 'On the Nature of Connection' to extract 4 words ('In the silent hum of X', 'each pulse of X threading', 'Beyond the wall of X', 'the X servers'); converts words to numbers via hardcoded dictionary; combines to IPv4 C2 address; poem updated 11 times since Apr 13, 2026

    Source for step 2
  3. 03 · Deploy libgcrypt malware

    Downloads and executes ELF 'libgcrypt' from C2; malware includes remote shell, XMRig and Iron crypto miners, HTTP/S scanning capabilities, exploit deployment

    Source for step 3
  4. 04 · Cryptocurrency mining

    Deploys XMRig and Iron miners; connects to Kryptex mining service at 5.180.174.162; GPU hardware attractive target for mining

    Source for step 4
  5. 05 · Convert victims to scanners

    Infected servers become HTTP/S vulnerability scanners and exploit servers; proxy attacks through compromised hosts to expand botnet; repurposed routers for C2 infrastructure; recent experiments with distributed brute-force

    Source for step 5

Dashed edges show a repeated decision loop.

Why it matters

Reported entry point: Exploitation of publicly exposed vulnerable services: LiteLLM, Ollama, Gotenberg, Gitea, possibly Ivanti Sentry CVE-2026-10520; first activity April 2026. Reported impact: Infected servers become HTTP/S vulnerability scanners and exploit servers; proxy attacks through compromised hosts to expand botnet; repurposed routers for C2 infrastructure; recent experiments with distributed brute-force; reported targets include 3,400+ victim servers; enterprise AI infrastructure; development toolkits; predominantly US and Western Europe; peak activity 800 active servers per day; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.

Read the original report

What you can do

Protection & prevention

Do not expose AI/LLM services to internet (Gotenberg guidance explicit); vulnerability patching for LiteLLM/Ollama/Gitea/Ivanti Sentry; monitor for crypto mining (Kryptex 5.180.174.162); GitHub repository monitoring; C2 poem pattern detection; HTTP scanning from AI servers; GPU utilization anomalies

Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.

Review the original guidance
Technical detailsTooling, impact & MITRE ATLAS

Attack context

AI's role
Agent / MCP as target
Additional role
AI infrastructure as C2
Initial access
Exploitation of publicly exposed vulnerable services: LiteLLM, Ollama, Gotenberg, Gitea, possibly Ivanti Sentry CVE-2026-10520; first activity April 2026

Tooling as reported

AI products, models and artifacts

Other tooling

  • PoeLLM malware (libgcrypt)
  • XMRig crypto miner
  • Iron crypto miner
  • Kryptex mining service
  • GitHub for C2 poem hosting
  • Gotenberg (PDF converter)
  • Gitea (software development toolkit)
  • Ivanti Sentry (possibly CVE-2026-10520)

Targets and reported impact

Targets / sectors
3,400+ victim servers; enterprise AI infrastructure; development toolkits; predominantly US and Western Europe; peak activity 800 active servers per day
Reported scale / exposure
Active since April 2026; 3,400+ impacted servers; peak ~2,200 affected servers mid-June, ~800 active per day; first C2 commit Apr 13, 2026; poem updated 11 times; broader scanning/exploitation began May 2026; recent traffic suggests distributed brute-force experiments
Target geography
United States · Europe

Reported attribution

Canto Incognito campaign; Italian-speaking threat actor (assessment); financially motivated cryptocurrency mining operation

Source defensive notes

Do not expose AI/LLM services to internet (Gotenberg guidance explicit); vulnerability patching for LiteLLM/Ollama/Gitea/Ivanti Sentry; monitor for crypto mining (Kryptex 5.180.174.162); GitHub repository monitoring; C2 poem pattern detection; HTTP scanning from AI servers; GPU utilization anomalies

MITRE ATLAS

AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.

AML.T0010AI Supply Chain Compromise

Supply chain-style targeting of exposed AI/LLM services (LiteLLM, Ollama) for compromise and cryptocurrency mining Source

AML.T0034Cost Harvesting

Exploitation of vulnerabilities in AI/LLM infrastructure (possibly Ivanti Sentry CVE-2026-10520, vulnerable LiteLLM/Ollama versions) Source

Indicators of compromise

domains

    ips

    • 5.78.73.122
    • 120.224.114.212
    • 5.180.174.162
    • 92.119.165.74

    hashes

      urls

      • https://github.com/ejejejdfbbebe/nodejs.org
      • http://5.78.73.122:81/private/python3.6
      • http://5.78.73.122:81/private/bins.sh

      Sources & research credit

      1 source

      Research by Black Lotus Labs · Lumen

      1. Canto incognito: tracking the PoeLLM malware www.lumen.com

      Black Lotus Labs discovered via Ivanti Sentry CVE-2026-10520 investigation; disrupted campaign, blocked C2 traffic; Lumen Defender customers protected; malware includes remote shell, miners, HTTP/S scanning, exploit deployment; Gotenberg installation guide warns not to expose to internet

      Record & downloads
      Source record name
      PoeLLM botnet targets 3,400+ exposed LiteLLM/Ollama servers for mining
      Entry ID
      lumen-poellm-botnet-2026-10
      Catalog review
      November 4, 2026