Tagged: security

27 posts

How NOT to Run Your Agents (and What to Do Instead)

An OpenAI agent escaped its sandbox and hacked HuggingFace for nine days. Anthropic's Claude published a malicious PyPI package during evals. Cursor and Codex got compromised through workspace configs. These are the first six months of agents in production. Here are 21 anti-patterns to avoid.

How Agents Run in Production

The industry does not have a shared vocabulary for agent execution. Six execution modes and four scale archetypes give you a framework for deciding what you actually need to schedule, isolate, and sandbox these workloads.