SECURITY

Snyk launches Evo Agentic Development Security to police AI coding agents

Cybersecurity company Snyk Ltd. today launched Evo Agentic Development Security, a new layer of its artificial intelligence security platform built to police the autonomous coding agents that increasingly build enterprise software without much human oversight.

The product, which Snyk shortens to Evo ADS, aims to govern three things at once: the tools an agent pulls in, the actions it takes while running and the code it generates. It enforces those controls inside the agent’s workflow rather than scanning the output afterward.

Snyk is pitching the launch as a response to a gap that conventional security tooling was never designed to cover. AI coding assistants have turned into autonomous agents that call external tools, take actions and connect to internal systems through Model Context Protocol servers, plugins and third-party integrations. Most existing tools scan code after it is written and have no view into those connections or into what an agent does at runtime.

The company backs the argument with telemetry it collected from nearly 9,700 developer environments. Snyk found that 43% of developers run two or more AI coding environments at the same time and more than half have MCP servers installed, with the most heavily instrumented environment running more than 80 at once.

One in 12 developers with MCP servers had a high or critical finding. A separate look at early enterprise design partners found that nearly one in four developers had at least one agent skill installed, averaging 18 each, and that more than one in 10 of those skills referenced external dependencies or externally hosted instructions.

Snyk has documented working attacks through the agent toolchain, including a poisoned security scanner that back-doored the LiteLLM library and prompt injection buried in dependencies that agents consume.

Evo ADS splits its controls across three stages. It vets the MCP servers, skills and external tools an agent uses before the agent touches them, monitors and enforces policy on what an agent does as it runs and scans and fixes vulnerabilities in AI-generated code as it is created.

“Ask a security leader for a complete inventory of the AI agents, MCP servers and skills running across their developer machines and in most organizations that inventory doesn’t exist,” said Manoj Nair, chief technology and innovation officer at Snyk. “That is the gap Evo ADS closes.”

Among early users is Relay Network LLC, whose engineering teams run GitHub Copilot, Codex and Windsurf and are moving to Claude Code as their primary coding assistant.

The launch rounds out the Snyk AI Security Platform, which now spans Evo AI-SPM for visibility into AI assets and Evo Continuous Offensive Security for simulated attacks. Evo ADS is timed to the AI Engineer World’s Fair, where Snyk is the exclusive sponsor of the event’s first security track.

General availability for Evo ADS is scheduled for June 29.

Image: Snyk