Apiiro launches command-line interface to bring AI-native security into software development workflows

Application security posture management company Apiiro Ltd. today announced the launch of a new command-line interface designed to bring application security directly into artificial intelligence-driven software development workflows as organizations grapple with the rapid rise of AI-generated code.

Apiiro CLI is targeting the growing gap in modern software development, where traditional security tools have been built for human developers reviewing code, not for AI agents that can generate and modify code at scale and speed. As AI-assisted development accelerates, the mismatch is creating new risks that existing tools struggle to address.

Apiiro argues that security workflows have become increasingly reactive and in 2026 are now relying on scanning and remediation after code has already been written. That model is hard to sustain when AI agents are producing large volumes of code faster than teams can review or validate it.

The Apiiro CLI shifts security to earlier in the development process by making it directly accessible to AI agents as they generate and modify code. The idea is that rather than relying solely on human oversight, the tool allows automated systems to incorporate security considerations in real time.

Underpinned by the Apiiro platform, AI agents gain visibility into application architecture, data flows and risk exposure to make more informed decisions during development.

The CLI acts as a bridge between that contextual intelligence and automated workflows by allowing AI agents to query security insights, apply policies and validate changes as part of continuous integration and delivery pipelines. As a result, security is embedded directly into development processes.

Apiiro CLI ships with six agent skills that offer structured capability definitions that AI coding assistants like Claude Code and Cursor can read and invoke autonomously. Easy to install with one command, AI assistants gain a clear understanding of what Apiiro can do and can invoke the right capability with the right software graph context.

The six skills are structured as discrete, trigger-based capabilities that allow AI assistants to take action at different stages of the development lifecycle without interrupting workflow.

Scan handles real-time detection of secrets and vulnerable dependencies, while Risks provides contextual access to Apiiro’s full risk inventory directly inside the coding environment. Fix then connects those findings to automated remediation, allowing AI agents to resolve issues in place, upgrading dependencies, removing exposed secrets or rewriting insecure code patterns as needed.

The other skills extend security further upstream and across the lifecycle.

Guardian Agent acts as a continuous, context-aware application security assistant that can answer questions about codebases and risk posture, while AI Threat Modeling introduces STRIDE-based analysis before code is written.

The final skill, Secure-Prompt, completes the loop by embedding security requirements into development tasks at the instruction stage, ensuring that AI-generated code is hardened from the outset rather than requiring fixes after the fact.

“AI is rewriting how software is built. Security platforms that weren’t designed for AI agents will become irrelevant because AI agents can’t interact with them,” said Shmulik Cohen, an AI engineer at Apiiro. “The Apiiro CLI is proof that being AI-native means more than using AI inside your platform. It means building a platform that AI can use.”

Apiiro has raised $135 million over two rounds, including $35 million in October 2020 and $100 million in November 2022. Investors include General Catalyst Group Management, Greylock Partners and Kleiner Perkins Caufield & Byers.

Image: SiliconANGLE/Ideogram