AI Infrastructure

Local LLM

The Model File Is the Payload: GGUF Parser Attack Surface and the Local AI Supply Chain

Four CVEs in the llama.cpp GGUF parser prove a model file is executable code at parse time; a Jinja2 SSTI in Python bindings and a server-side completion-endpoint RCE broaden the surface. What six bugs mean for Ollama, LM Studio, and your homelab intake process.

Self-Hosting

BadHost in My Own Rack: Auditing a Self-Hosted AI Stack for the Starlette Host-Header Bypass

I audited my self-hosted AI stack against CVE-2026-48710 (BadHost), the Starlette host-header auth bypass. One component ran an affected version and stayed protected by code, not by patch. The exact per-container checks, and the scan that exposed it.

research

Detection Guidance: Auditing Your Homelab for Exposed MCP Servers

Hands-on checklist for homelab operators: detect, fingerprint, and harden exposed MCP endpoints running on Ollama, Claude Code agents, or custom self-hosted AI services. Based on Trend Micro research documenting ~1,500 unauthenticated servers in 2026.

langflow

Langflow Vulnerability Cluster: CVE-2025-3248 + CVE-2026-5027 — Active Exploitation Analysis and Homelab Impact

Langflow has THREE critical vulnerabilities actively exploited in the wild. With ~7,000 instances exposed on public internet and auto-login enabled by default, homelab operators are prime targets.

AI/LLM Generated

AI Agent Least Privilege: Securing MCP and Tool-Using Workflows

A practical guide to applying least privilege, scoped identities, approval gates, and observability to MCP and tool-using AI workflows.

AI/LLM Generated

Ollama on the Open Internet: 300,000 Exposed AI Inference Servers Under Active Attack

GreyNoise honeypot data reveals 300,000+ Ollama instances exposed to the internet. Bleeding Llama (CVE-2026-7482), LLMjacking campaigns, and agentic weaponization represent an escalating threat to homelab AI deployments.