Cycode Launches Workstation Protection for Developer Security

0
Cycode has introduced Workstation Protection, a new capability designed to provide real-time security for developer workstations. The technology aims to address AI-driven software supply chain risks by detecting and blocking malicious packages before they can be installed, extending application security protections directly into developer environments.

Cycode ADLC Protection intercepts package installs in real time and evaluates them before they reach the machine, applying two controls:

  • Enforcing cooldown policies. Release-age gating refuses versions published too recently to have been scrutinized, the window in which compromised releases are most often caught. Because enforcement happens on the device, the policy holds no matter which package manager version a developer or agent is running, or whether a local configuration was ever applied.
  • Blocking known-malicious packages. Each install is checked against a continuously updated threat intelligence feed. Confirmed-malicious packages are stopped regardless of when they were published, including older versions and versions that have already aged past a cooldown window.

AI development increases software supply chain attack risks

Software supply chain attacks increasingly target workstations, installing malicious packages to harvest credentials, establish persistence, and compromise the supply chain before a line of code is generated or a security check runs.

These attacks have grown more prevalent as attackers exploit two weaknesses: hijacking maintainer accounts to weaponize trusted open-source packages, and manipulating coding agents into installing malicious packages. The result is more attacks and a wider target. Once limited to developers & their SCM, the attack surface now extends to every developer workstation running a coding agent.

Recent attacks include:

  • Keyv, August 2026. A hijacked maintainer account seeded a preinstall worm across 800+ packages and 1,300+ versions representing more than two billion monthly installs, harvesting cloud and CI credentials.
  • LiteLLM, March 2026. Attackers published two malicious packages in a library with 95 million monthly downloads that triggered credential theft, Kubernetes lateral movement, and a persistent backdoor.
  • Shai-Hulud 2.0, November 2025. A self-replicating npm worm reached roughly 350 maintainers and exfiltrated secrets to more than 25,000 attacker-created GitHub repositories.

“Risk enters the agentic development lifecycle (ADLC) for our customers before a single line of code is generated. Developers connect AI tools nobody approved, agents install packages nobody reviewed, and secrets leak into prompts and file reads nobody sees,” said Seth Robbins, President of Cycode. “ This launch extends Cycode’s platform to the workstation, the earliest control point in the software supply chain where malicious packages are installed and must be stopped.”

Cycode stops software supply chain attacks before they start

Cycode Workstation Protection deploys through Mobile Device Management, adds no console or infrastructure, and changes nothing about how developers install packages. Security teams define and manage cooldown policies centrally, so protection extends to every developer workstation running a coding agent as quickly as software can be pushed to it.

Workstation Protection extends Cycode ADLC Security, which covers each moment risk enters agentic development. It begins on the device, where malicious packages install before a line of code is written. It continues into the AI tools developers adopt, where visibility and governance surface shadow AI, coding assistants, and MCP servers and control what is permitted.

It reaches the prompt, where guardrails stop risky behaviors like exposing secrets in prompts and file reads. And it extends into the code agents generate, which Cycode secures before it ships. Every signal resolves in the Context Intelligence Graph, giving security teams one view of risk across the lifecycle and one place to act on it.

“Security has to start where risk enters the development lifecycle, not after,” said Dor Atias, Co-Founder and Chief Product and Engineering Officer at Cycode. “Blocking malicious packages is the earliest control point in a complete agentic development and software supply chain security solution. Protect every workstation. Control every input. Secure every output. That is what unlocks secure AI development.”

For more information, visit: https://cycode.com/blog/introducing-workstation-protection/

Related News:

The Impact of Agentic AI on Network Operations Released by Cisco

IDTrust Brings Verifiable AI Agent Identity to IBM Cloud

Share.

About Author

Leigh Porter's first love is to love people. Beginning her career as a neonatal RN was an obvious choice until life threw the curve ball to embark on a new IT endeavor. Pursuing this fresh career was a piece of cake with her resilient and steadfast character. Outside of the office, Leigh also diligently gives much of her time faithfully as a nationally awarded volunteer leader to a very dear to her heart organization.