{
  "id": "sysdig-attacker-turns-hijacked-ollama-server-2026-06",
  "name": "Sysdig: attacker turns hijacked Ollama server into reasoning engine for an autonomous exploit pipeline",
  "date_reported": "2026-06-17",
  "researcher": "unknown",
  "org": "Sysdig Threat Research Team",
  "sources": [
    {
      "url": "https://webflow.sysdig.com/blog/llmjacking-evolved-attackers-are-using-stolen-ai-compute-to-build-offensive-agentic-tools",
      "publisher": "Sysdig Threat Research Team"
    },
    {
      "url": "https://labs.cloudsecurityalliance.org/research/csa-research-note-llmjacking-offensive-agentic-infrastructur/"
    }
  ],
  "borderline": false,
  "ai_role": "attacker_uses_ai_as_operator",
  "ai_role_secondary": "ai_credential_theft",
  "technique_summary": "Instead of reselling stolen AI compute, an actor used a free exposed Ollama model as the brain of a multi-stage autonomous scanning and exploitation tool under active development.",
  "initial_access": "unknown",
  "ai_tooling_and_models": [
    "Internet-exposed Ollama servers",
    "tool requested OpenAI, Anthropic and Google model names"
  ],
  "other_tooling": [],
  "victims_and_sectors": "Technology and AI companies; Multiple sectors",
  "regions": [
    "unknown"
  ],
  "region_notes": "Target geography was not captured by the Notion feed. Actor attribution is not used as a victim location.",
  "attribution_or_cluster": "Unnamed (VAPT tool developer; source IPs in India)",
  "scale_and_metrics": "unknown",
  "prevention_angle": "unknown",
  "related_magicsword_projects": [],
  "source_notes": "Imported from the AI Threat Watch Notion feed (an automated daily scan); not yet editorially reviewed. Feed severity: Medium. Feed novelty: New TTP.",
  "tags": [
    "notion-import",
    "api-key-account-abuse",
    "agentic-operations",
    "vuln-discovery-exploit"
  ],
  "category": "adversary-use-of-ai",
  "ai_involvement_confidence": "confirmed"
}