Security

The Chaindrop npm worm, the newest strain in the Shai-Hulud family, runs on install and steals every credential the build can reach. Here is how a team already running Hyground scopes the exposure, proves whether it executed, and rotates what it touched, with every destructive fix behind human approval.

A working demo takes a weekend. A production-grade AI SRE agent your on-call team trusts is roughly 5 to 7 senior engineers for a year to a credible first version, plus a permanent team to keep it there. An honest build vs buy accounting of what the demo hides.

Executives say they trust AI agents to act during incidents. The engineers on call mostly don't. This post sides with the engineers, then walks through the architecture that makes the trust question smaller: read-only defaults, evidence-linked findings, approval-gated writes, and an audit trail.

Twenty OWASP risks, but for an AI SRE agent they can be collapsed into five hard hurdles between a working demo and production you can trust.

OWASP's Top 10 for Agentic Applications is the threat model for AI agents in production systems. Here is what each of the ten risks means for an AI SRE agent.

OWASP's LLM Top 10 turns from an abstract risk list into a concrete architecture spec the moment you put an AI agent inside your operations loop.