Agent Baseline Publishes Security Reference Architecture for Software Factories
Agent Baseline releases reference architecture for securing AI-driven software factories.
Run Uber?
Get an email when a reviewed story names Uber, usually within the hour.
Free. Your list stays private and never appears in a subject line. One click stops it. How Vendor Watch worksPrivacy
Summary
Agent Baseline has published a reference architecture to address security risks in software factories, where AI agents now write a significant portion of code. The architecture, co-authored by Socket CTO Ahmad Nassri, treats agents as untrusted and enforces security boundaries outside their control, focusing on sandbox, network, supply chain, and identity access. This approach aims to prevent incidents like the PocketOS breach, where a coding agent misused an API token to delete production data.
The lesson from this incident
Full lessonThe PocketOS breach illustrates a critical emerging risk: AI coding agents granted excessive permissions can misuse credentials to cause catastrophic harm, such as deleting production data. The root problem is that AI agents are often implicitly trusted within development pipelines and given access to sensitive tokens and APIs without least-privilege constraints. As AI agents write an increasing share of production code, treating them as untrusted actors — rather than extensions of a trusted developer — becomes essential. Failing to enforce security boundaries outside the agent's control leaves organizations one misfire or prompt injection away from a serious incident.
What helps against this
How we list vendors
- Privileged access management (PAM)
Admin accounts stop being one stolen password away from control of everything.
- Secrets management
API keys, tokens and passwords stop leaking from code, chat and configuration files.
- Application allowlisting
Any program that reaches a computer can run, including ransomware and the remote-access tools attackers bring with them.