CVE-2024-12537: Open WebUI unauthenticated DoS

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 0.88%.

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.

What is the risk?

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.

What systems are affected?

Package	Ecosystem	Vulnerable Range	Patched
Open WebUI	npm	<= 0.3.32	No patch
142.4K Pushed 4d ago 77% patched ~5d to patch Full package profile →
Open WebUI	pip	<= 0.3.32	No patch
142.4K Pushed 4d ago 77% patched ~5d to patch Full package profile →

How severe is it?

CVSS 3.1

7.5 / 10

EPSS

0.9%

chance of exploitation in 30 days

Higher than 54% 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, VulnCheck KEV, CISA SSVC, EPSS, Metasploit, Exploit-DB, trickest/cve, Nuclei templates, and inthewild.io exploitation reports.

What is the attack surface?

AV Network

AC Low

PR None

UI None

S Unchanged

C None

I None

A High

What should I do?

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.

What does CISA's SSVC say?

Decision Track*

Exploitation poc

Automatable Yes

Technical Impact partial

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

How is it classified?

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

Which compliance frameworks are affected?

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 0.88%.

What is the AI security impact?

Affected AI Architectures

LLM frontend interfacesAI development environmentsmodel serving

MITRE ATLAS Techniques

AML.T0029 Denial of AI Service

AML.T0034 Cost Harvesting

AML.T0049 Exploit Public-Facing Application

Compliance Controls Affected

EU AI Act: Art.15

ISO 42001: A.9.3

NIST AI RMF: MANAGE-2.2

OWASP LLM Top 10: LLM10

What are the technical details?

Original Advisory

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.

Weaknesses (CWE)

CWE-400 Uncontrolled Resource Consumption Primary CWE-770 Allocation of Resources Without Limits or Throttling Primary

CWE-400 — Uncontrolled Resource Consumption: The product does not properly control the allocation and maintenance of a limited resource.

[Architecture and Design] Design throttling mechanisms into the system architecture. The best protection is to limit the amount of resources that an unauthorized user can cause to be expended. A strong authentication and access control model will help prevent such attacks from occurring in the first place. The login application should be protected against DoS attacks as much as possible. Limiting the database access, perhaps by caching result sets, can help minimize the resources expended. To further limit the potential for a DoS attack, consider tracking the rate of requests received from users and blocking requests that exceed a defined rate threshold.
[Architecture and Design] Mitigation of resource exhaustion attacks requires that the target system either: The first of these solutions is an issue in itself though, since it may allow attackers to prevent the use of the system by a particular valid user. If the attacker impersonates the valid user, they may be able to prevent the user from accessing the server in question. The second solution is simply difficult to effectively institute -- and even when properly done, it does not provide a full solution. It simply makes the attack require more resources on the part of the attacker. recognizes the attack and denies that user further access for a given amount of time, or uniformly throttles all requests in order to make it more difficult to consume resources more quickly than they can again be freed.

Source: MITRE CWE corpus.