CVE-2024-37032 — HIGH (CVSS 8.8) AI Security Vulnerability

CISO Take

Ollama before 0.1.34 contains a path traversal flaw (CWE-22) in its model blob API that enables remote code execution with low privileges and no user interaction required. Any team running Ollama—locally or network-exposed—must upgrade to 0.1.34+ immediately. If Ollama is accessible beyond localhost, treat it as potentially compromised and audit access logs for '../' patterns in blob requests.

Risk Assessment

High risk (CVSS 8.8). Network-accessible, low-complexity, no user interaction required—trivially exploitable by any user with API access. Ollama's default port (11434) is frequently left open on internal networks or exposed externally in development environments. A public exploit write-up ('Probllama' via Vicarius) is available, materially lowering the bar for exploitation. No active KEV listing, but public PoC makes exploitation highly likely.

Affected Systems

Package	Ecosystem	Vulnerable Range	Patched
ollama	pip	—	No patch
171.1K 1.5K dependents Pushed today 4% patched ~0d to patch Full package profile →

Do you use ollama? You're affected.

Severity & Risk

CVSS 3.1

8.8 / 10

EPSS

93.7%

chance of exploitation in 30 days

Higher than 100% of all CVEs

Source: EPSS v3 — FIRST.org

Exploitation Status

Actively Exploited

Sophistication

Trivial

Exploitation Confidence

high

✓ CISA KEV (active exploitation confirmed)

○ Public PoC indexed (trickest/cve)

○ EPSS exploit prediction: 94%

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

Attack Surface

AV Network

AC Low

PR Low

UI None

S Unchanged

C High

I High

A High

Recommended Action

1 step

1) Upgrade Ollama to 0.1.34+ immediately—this is the only complete fix. 2) If patching is delayed, restrict API to localhost by binding to 127.0.0.1 and block port 11434 at the network perimeter. 3) Run Ollama in a container with a read-only root filesystem and minimal volume mounts to limit blast radius. 4) Search access logs for blob path requests where the digest field contains '../' or strings not matching the pattern [a-f0-9]{64}. 5) Audit who has network access to Ollama—by default it has no authentication layer.

CISA SSVC Assessment

Decision Track

Exploitation none

Automatable No

Technical Impact partial

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

Classification

Code Execution Data Extraction Inference Framework API AML.T0010.001 - AI Software AML.T0025 - Exfiltration via Cyber Means AML.T0040 - AI Model Inference API Access AML.T0049 - Exploit Public-Facing Application

Compliance Impact

This CVE is relevant to:

EU AI Act

Article 15 - Accuracy, robustness and cybersecurity

ISO 42001

A.9.4 - Information security for AI systems

NIST AI RMF

MANAGE 2.2 - Mechanisms to sustain effectiveness of AI risk or impact mitigations are planned

OWASP LLM Top 10

LLM05 - Supply Chain Vulnerabilities

Frequently Asked Questions

What is CVE-2024-37032?

Ollama before 0.1.34 contains a path traversal flaw (CWE-22) in its model blob API that enables remote code execution with low privileges and no user interaction required. Any team running Ollama—locally or network-exposed—must upgrade to 0.1.34+ immediately. If Ollama is accessible beyond localhost, treat it as potentially compromised and audit access logs for '../' patterns in blob requests.

Is CVE-2024-37032 actively exploited?

Yes, CVE-2024-37032 is confirmed actively exploited and listed in CISA Known Exploited Vulnerabilities catalog.

How to fix CVE-2024-37032?

1) Upgrade Ollama to 0.1.34+ immediately—this is the only complete fix. 2) If patching is delayed, restrict API to localhost by binding to 127.0.0.1 and block port 11434 at the network perimeter. 3) Run Ollama in a container with a read-only root filesystem and minimal volume mounts to limit blast radius. 4) Search access logs for blob path requests where the digest field contains '../' or strings not matching the pattern [a-f0-9]{64}. 5) Audit who has network access to Ollama—by default it has no authentication layer.

What systems are affected by CVE-2024-37032?

This vulnerability affects the following AI/ML architecture patterns: local LLM inference, model serving, agent frameworks, self-hosted LLM APIs, AI development environments.

What is the CVSS score for CVE-2024-37032?

CVE-2024-37032 has a CVSS v3.1 base score of 8.8 (HIGH). The EPSS exploitation probability is 93.75%.

Technical Details

NVD Description

Ollama before 0.1.34 does not validate the format of the digest (sha256 with 64 hex digits) when getting the model path, and thus mishandles the TestGetBlobsPath test cases such as fewer than 64 hex digits, more than 64 hex digits, or an initial ../ substring.

Exploitation Scenario

An attacker with network access to Ollama's API (default port 11434) crafts a request to the blob endpoint using a malformed digest containing a path traversal sequence—e.g., 'sha256:../../../etc/cron.d/pwned'. Since Ollama does not validate the digest format, it resolves this to an arbitrary filesystem path. The attacker writes a cron job, an SSH authorized_keys entry, or a reverse shell payload to the host, achieving persistent access to the machine running the LLM inference server. In enterprise environments, this host often has broad internal network access and stores sensitive model weights or API credentials.