• AI services
  • Service discovery
  • Infrastructure assessment
Home/Projects/aipostex
Project 03v1.14.3

aipostex

Offensive security framework for AI infrastructure: the services around the model, not the model itself.

professor-moody.github.io

Research focus.

Discovery, assessment, and exploitation across 20+ AI services including Ollama, vector databases, Jupyter, Kubernetes, and model serving platforms. 131 vulnerability templates (85 detection, 46 exploit), 20 exploit modules, and 30 HTTP service fingerprint probes. Safe by default, since scans run in detect mode and active exploitation requires an explicit flag. Stealth mode covers request jitter, User-Agent rotation, and proxy support.

Read into the work.

2 essays
  1. A Field Guide to AI Infrastructure

    8 min read
  2. The Tunnels Under the Surface

    8 min read
← All projects