A $60/Month VM Running an LLM Agent Now Does Autonomous Security Work

Ivan Novikov, CEO of Wallarm, posted a claim on X yesterday that pulled 2.5k impressions in its first hours: it has never been this easy to run cybersecurity autonomously. His setup is a dedicated virtual machine — about $60 per month — with an LLM agent on it that never pushes back on security work.

The refusal problem he's solving

Public coding assistants come with guardrails. Novikov's dig is aimed at Claude Code: in his experience it either refuses security-related tasks outright or silently switches you to an older, less capable model when the work gets sensitive. For a security engineer, a tool that negotiates is a tool that fails at the worst moment.

A dedicated VM removes the negotiation. The model inside has no policy layer to trip over, and nobody throttles it mid-scan.

The actual workflow

The setup is one prompt long. You tell the agent to install Sourcegraph for semantic code search or xerj.org for patch and impact analysis. From that point it runs unattended:

• Patch hunting — the agent scans source code for incomplete patches: fixes that were reverted, partially applied, or quietly dropped in a later refactor
• Runtime tracing — suspected issues get validated by observing execution, so the report isn't a pile of static-analysis false positives
• Persistence — it keeps going for days, iterating over the codebase without a human driving each step

That last part is the actual shift. Security tooling has always been good at finding candidate bugs; the expensive part was a human verifying them. An agent that both hunts and validates compresses that loop.

The economics

$60 a month is less than an hour of a junior security analyst's time in most markets. The agent works around the clock and doesn't context-switch. Novikov's summary: "I feel like I woke up."

The obvious caveats

An agent with no pushback also has no brakes. It will happily scan code it has no permission to touch, and its findings still need human review before anyone acts on them. Autonomy changes who does the boring work — it doesn't remove accountability.

Source: Ivan Novikov on X