Deep-dive guides on AI agents, agent orchestration, MCP, and developer tooling.
2 posts found
Coding agents now run arbitrary, LLM-generated code by default — npm install, test suites, shell one-liners — which turns "sandbox untrusted code" from an occasional need into a load-bearing part of the architecture. Here's what actually stands between an agent's code and your host kernel.
Most agent security advice targets prompt injection at the wrong layer. The real fix is architectural: separate untrusted tool output from privileged context, scope tool capabilities narrowly, and gate side-effecting actions behind confirmation.