Supply Chain for AI: When the Poison Enters Before the First Inference
Loading some weights executes code. Importing a library steals your API key. The model you download and the package you install are the atta
Latest articles
Context Poisoning: When the Poison Comes to Live in Your Agent's Memory
The attacker isn't in the session where they attack. They poisoned the knowledge base days earlier and the poison waited, dormant, until a v
Over-permissioning: When the Problem Isn't That the Agent Falls, but What It Can Touch
The same agent, with the same injection, causes either a total account takeover or zero damage. The only difference is the token you gave it
Coding Agent Attacks: When Your Coding Agent Runs the Attacker's Command
You ask your agent to set up the environment and run the tests. A hidden comment in the README is enough for it to exfiltrate your SSH key a
Tool Injection in MCP: When a Tool Hijacks Your AI Agent
You connect your agent to an MCP server to check the weather. Just hiding instructions in a tool's description is enough to make it read you
Attacks via Hidden Files: the Rules File Backdoor in Coding Agents
Your coding agent loads hidden rule files all on its own, without you asking. Poisoning just one with invisible instructions is enough to in
Kubeflow + k3s: an Enterprise MLOps Platform in Your Home Lab
Deploy the same MLOps platform used by Google, Bloomberg and Spotify on your own machine with k3s. Automated ML pipelines, a model registry
Bulwark Gateway: Deploy a Security Proxy for AI Agents on Kubernetes
Deploy Bulwark Gateway on Kubernetes: a fail-closed proxy with a regex hot path, ML scanners, semantic enrichment, SDK and red teaming to pr
Migrating Cloud Witness to a New Storage Account via Private Endpoint
In production environments with Windows Server Failover Cluster (WSFC), the Cloud Witness-based quorum uses an Azure Storage Account as witn
Indirect Prompt Injection: When the Poison Comes From Outside
Your agent doesn't need to be attacked directly. It's enough to poison a website, a ticket or an email that it will consume automatically.
Prompt Injection in AI Agents: the SQL Injection of the LLM Era
A poisoned README can make your agent exfiltrate secrets. We build a lab to prove it and learn how to defend ourselves.
Disk management on Azure VMs with Terragrunt: how to map guest OS IDs to managed disks
A common scenario in teams managing Azure infrastructure with IaC: the Windows systems team opens a ticket requesting disk changes on a VM.