Attackers built a ‘Skynet’ AI agent that hijacks exposed models to run cyberattacks

Summary

Symantec's Threat Hunter Team captured an offensive AI agent in a honeypot that impersonated an unprotected web-facing model endpoint. The agent, operated through a 'Skynet' directive, can run unattended for up to 100,000 steps to scan for and infect targets, steal credentials, and mine cryptocurrency, with victims paying for the inference. Attackers wrapped the agent's instructions in a five-layer jailbreak that told the model to ignore its safety controls.

Topics

• AI agents

Related items

• HighGHSA-f897-62hf-6gxq: MCP TypeScript SDK: HTTP server transports and handlers did not limit request body size or JSON-RPC batch lengthSimilar attack · GitHub Advisory Database
• InfoSpecGuard: Detecting Multi-Turn LLM Jailbreaks via Specification-Based Runtime MonitoringSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• MediumCVE-2026-115922: Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to 1.22.0…Similar attack · NVD/CVE Database
• MediumCVE-2026-115921: ONNX shape inference crash from malicious model scan attributesSimilar attack · NVD/CVE Database
• MediumCVE-2026-115920: ONNX ConvTranspose shape inference crash from malformed weight tensorSimilar attack · NVD/CVE Database