CVE-2024-12537 — HIGH (CVSS 7.5) AI Security Vulnerability

Q: Is CVE-2024-12537 actively exploited?

No confirmed active exploitation of CVE-2024-12537 has been reported, but organizations should still patch proactively.

Q: How to fix CVE-2024-12537?

1. Immediately add request body size limits at the reverse proxy layer (e.g., nginx `client_max_body_size 1m` or equivalent in Caddy/Traefik). 2. Apply rate limiting to the `/api/v1/utils/code/format` endpoint — no more than 10 requests/minute per IP. 3. Restrict the endpoint to authenticated internal networks or VPN; it should never be publicly reachable. 4. Upgrade Open-WebUI beyond version 0.3.32 as soon as a patched release is confirmed — no patch is currently available. 5. Add monitoring for anomalous POST request sizes or sustained high latency on this endpoint as an early warning signal. 6. Consider a WAF rule to block payloads exceeding 512KB to this specific path.

Q: What systems are affected by CVE-2024-12537?

This vulnerability affects the following AI/ML architecture patterns: LLM frontend interfaces, AI development environments, model serving.

Q: What is the CVSS score for CVE-2024-12537?

CVE-2024-12537 has a CVSS v3.1 base score of 7.5 (HIGH). The EPSS exploitation probability is 2.67%.

CISO Take

Open-WebUI's code formatting endpoint is reachable without authentication, allowing any internet attacker to exhaust server resources with oversized POST requests and take down your entire AI interface. If running Open-WebUI ≤0.3.32 with any public exposure, enforce request body size limits at the reverse proxy immediately and restrict endpoint access to authenticated networks. Upgrade as soon as a patched release is confirmed.

Risk Assessment

Risk is HIGH for organizations exposing Open-WebUI publicly — common in enterprise AI labs and development environments running Ollama or OpenAI-compatible backends. The vulnerability requires no credentials, no AI/ML knowledge, and no special tooling; a script sending oversized HTTP payloads is sufficient. Impact is limited to availability (no data leakage, no code execution), consistent with CVSS 7.5. EPSS of 0.77% reflects low automated exploitation activity today, but trivial exploitability means any motivated actor can cause sustained disruption at near-zero cost.

Affected Systems

Package	Ecosystem	Vulnerable Range	Patched
open-webui	npm	<= 0.3.32	No patch
135.3K Pushed 8d ago 58% patched ~9d to patch Full package profile →
open-webui	pip	<= 0.3.32	No patch
135.3K Pushed 8d ago 58% patched ~9d to patch Full package profile →

Severity & Risk

CVSS 3.1

7.5 / 10

EPSS

2.7%

chance of exploitation in 30 days

Higher than 86% of all CVEs

Source: EPSS v3 — FIRST.org

Exploitation Status

Exploit Available

Exploitation: MEDIUM

Sophistication

Trivial

Exploitation Confidence

medium

○ CISA SSVC: Public PoC

Composite signal derived from CISA KEV, CISA SSVC, EPSS, trickest/cve, and Nuclei templates.

Attack Surface

AV Network

AC Low

PR None

UI None

S Unchanged

C None

I None

A High

Recommended Action

6 steps

Immediately add request body size limits at the reverse proxy layer (e.g., nginx client_max_body_size 1m or equivalent in Caddy/Traefik).
Apply rate limiting to the /api/v1/utils/code/format endpoint — no more than 10 requests/minute per IP.
Restrict the endpoint to authenticated internal networks or VPN; it should never be publicly reachable.
Upgrade Open-WebUI beyond version 0.3.32 as soon as a patched release is confirmed — no patch is currently available.
Add monitoring for anomalous POST request sizes or sustained high latency on this endpoint as an early warning signal.
Consider a WAF rule to block payloads exceeding 512KB to this specific path.

CISA SSVC Assessment

Decision Track*

Exploitation poc

Automatable Yes

Technical Impact partial

Source: CISA Vulnrichment (SSVC v2.0). Decision based on the CISA Coordinator decision tree.

Classification

DoS Auth Bypass API Framework AML.T0029 - Denial of AI Service AML.T0034 - Cost Harvesting AML.T0049 - Exploit Public-Facing Application

Compliance Impact

This CVE is relevant to:

EU AI Act

Art.15 - Accuracy, robustness and cybersecurity

ISO 42001

A.9.3 - AI system operation and monitoring

NIST AI RMF

MANAGE-2.2 - Mechanisms to sustain AI risk management plans

OWASP LLM Top 10

LLM10 - Unbounded Consumption

Frequently Asked Questions

What is CVE-2024-12537?

Open-WebUI's code formatting endpoint is reachable without authentication, allowing any internet attacker to exhaust server resources with oversized POST requests and take down your entire AI interface. If running Open-WebUI ≤0.3.32 with any public exposure, enforce request body size limits at the reverse proxy immediately and restrict endpoint access to authenticated networks. Upgrade as soon as a patched release is confirmed.

Is CVE-2024-12537 actively exploited?

No confirmed active exploitation of CVE-2024-12537 has been reported, but organizations should still patch proactively.

How to fix CVE-2024-12537?

1. Immediately add request body size limits at the reverse proxy layer (e.g., nginx `client_max_body_size 1m` or equivalent in Caddy/Traefik). 2. Apply rate limiting to the `/api/v1/utils/code/format` endpoint — no more than 10 requests/minute per IP. 3. Restrict the endpoint to authenticated internal networks or VPN; it should never be publicly reachable. 4. Upgrade Open-WebUI beyond version 0.3.32 as soon as a patched release is confirmed — no patch is currently available. 5. Add monitoring for anomalous POST request sizes or sustained high latency on this endpoint as an early warning signal. 6. Consider a WAF rule to block payloads exceeding 512KB to this specific path.

What systems are affected by CVE-2024-12537?

This vulnerability affects the following AI/ML architecture patterns: LLM frontend interfaces, AI development environments, model serving.

What is the CVSS score for CVE-2024-12537?

CVE-2024-12537 has a CVSS v3.1 base score of 7.5 (HIGH). The EPSS exploitation probability is 2.67%.

Technical Details

NVD Description

In version 0.3.32 of open-webui/open-webui, the absence of authentication mechanisms allows any unauthenticated attacker to access the `api/v1/utils/code/format` endpoint. If a malicious actor sends a POST request with an excessively high volume of content, the server could become completely unresponsive. This could lead to severe performance issues, causing the server to become unresponsive or experience significant degradation, ultimately resulting in service interruptions for legitimate users.

Exploitation Scenario

An attacker discovers an Open-WebUI instance via Shodan or targeted scanning — the tool is commonly deployed on internal ports exposed through reverse proxies, sometimes publicly. Without any credentials, they craft a script sending repeated POST requests to `/api/v1/utils/code/format` with payloads of several hundred megabytes. Within minutes, the server's thread pool and memory are exhausted, making the entire AI interface unavailable for all users. Developers lose access to their LLM workflows, automated pipelines time out, and the underlying models become unreachable. The attack sustains indefinitely at minimal attacker cost and requires only basic HTTP scripting knowledge.