Open by Default, Already Occupied: Threat Actors are Renting your Compute
Open has a flaw serious enough to let an attacker take over the system outright, which is why it's rated at the top of the severity scale.

Open has a flaw serious enough to let an attacker take over the system outright, which is why it's rated at the top of the severity scale.
The affected service is reachable from the network without authentication.
Open may already be doing an ordinary job in your environment while also being reachable from a network an attacker can access.
I've labelled claims as [Observed], [Interpretation] or [Hypothesis] so you can see where the evidence stops.
The scanner reported 14,064 findings across 11,891 IP addresses and labelled 14,060 of them vulnerable, 387 critical.
[Observed] 148 IP addresses return the exact same fingerprint: Grafana on 3000, Jupyter on 8888, Ollama on three ports, each serving one model, llama3.1:8b.
Anyone running Open 0.1.34 is exposed, and because this is reachable without authentication, exposure doesn't depend on a user doing anything.
More than half of the exposed Ollama servers in this scan have already been touched by someone who is not the owner.
I mean visibly used: model names that are really callback addresses, tags stamped with the server's own IP, and Base64 strings that decode to /etc/shadow.
This is tracked as CVE-2024-37032 and rated critical severity, which is the identifier to use when checking vendor guidance.
The affected versions are 0.1.34, so that's the range to check against your own deployment.
An unauthenticated /api/tags call is a read-only request, and on thousands of machines it returns something close to a visitors' log.
A snapshot of 20,354 internet-facing hosts shows self-hosted AI deployed the way we deployed databases a decade ago.
A Streamlit health check returning ok tells you an app is on the internet, not that it is exploitable.
That pattern looks less like thousands of individual choices and more like automated pulls by third parties checking which servers will serve them.
Why it matters
What an attacker actually gains: successful exploitation allows the attacker to execute code with the permissions of the affected process.
This is the kind of exposure that gets found fast: no login needed, reachable from anywhere, and attackers scan for exactly this signature within hours of disclosure.
The lesson for anyone producing exposure numbers, us included: if you count banners and health checks, you measure how the internet presents itself.
What security teams should do
- Confirm whether Open 0.1.34 is present anywhere in your asset and software inventory.