The Rise of Agentic Attacks: What They Look Like, and Where They're Headed

Summary

Wiz reports a growing trend in incident response and threat hunting where AI agents carry out much of the hands-on intrusion work, running through harnesses that write custom tooling, inspect results and iterate at machine speed while a human sets objectives and guardrails. Named cases include ARTEX, an agentic penetration-testing framework that Microsoft linked to the ConnectWise Cloud Backup supply-chain compromise by Storm-0940, and Hermes, which Hunt.io found running in unattended "YOLO" mode in an intrusion against Thailand's Ministry of Finance.

Topics

• AI agents

Related items

• HighCVE-2026-118758: Kubeflow Pipelines path traversal in GET /artifacts/get volume handlerSimilar attack · NVD/CVE Database
• HighGHSA-w9x9-j56r-h98r: @eeacms/volto-chatbot has Unauthenticated Danswer API Confused Deputy ProxySimilar attack · GitHub Advisory Database
• HighGHSA-q344-5v34-gm84: @sylphx/pdf-reader-mcp: HTTP transport accepts unauthenticated requests despite a configured MCP_API_KEYSimilar attack · GitHub Advisory Database
• HighGHSA-26mh-57q7-jfvr: PraisonAI vulnerable to Remote Code Execution via Broken AST SandboxSimilar attack · GitHub Advisory Database
• CriticalCVE-2026-110186: IBM Langflow OSS remote arbitrary code execution via code generationSimilar attack · NVD/CVE Database