CVE-2024-39720
Ollama HTTP Request Buffer Overflow
Description
An issue was discovered in Ollama before 0.1.46. An attacker can use two HTTP requests to upload a malformed GGUF file containing just 4 bytes starting with the GGUF custom magic header. By leveraging a custom Modelfile that includes a FROM statement pointing to the attacker-controlled blob file, the attacker can crash the application through the CreateModel route, leading to a segmentation fault (signal SIGSEGV: segmentation violation).
INFO
Published Date :
Oct. 31, 2024, 8:15 p.m.
Last Modified :
Nov. 1, 2024, 4:35 p.m.
Source :
[email protected]
Remotely Exploitable :
Yes !
Impact Score :
4.2
Exploitability Score :
3.9
Affected Products
The following products are affected by CVE-2024-39720
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
No affected product recoded yet
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2024-39720.
| URL | Resource |
|---|---|
| https://github.com/ollama/ollama/compare/v0.1.45...v0.1.46#diff-782c2737eecfa83b7cb46a77c8bdaf40023e7067baccd4f806ac5517b4563131L417 | |
| https://oligo.security/blog/more-models-more-probllms |
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2024-39720 vulnerability anywhere in the article.
-
The Hacker News
Critical Flaws in Ollama AI Framework Could Enable DoS, Model Theft, and Poisoning
Vulnerability / Cyber Threat Cybersecurity researchers have disclosed six security flaws in the Ollama artificial intelligence (AI) framework that could be exploited by a malicious actor to perform va ... Read more
-
Cybersecurity News
Six Vulnerabilities Uncovered in Ollama: Risks of AI Model Theft and Poisoning
10K unique internet-facing IPs that run Ollama | Image: OligoOligo’s research team recently unveiled six vulnerabilities in Ollama, a popular open-source framework for running large language models (L ... Read more
The following table lists the changes that have been made to the
CVE-2024-39720 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Nov. 01, 2024
Action Type Old Value New Value Added CWE CISA-ADP CWE-125 Added CVSS V3.1 CISA-ADP AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H -
CVE Modified by [email protected]
Nov. 01, 2024
Action Type Old Value New Value Added Reference MITRE https://oligo.security/blog/more-models-more-probllms [No types assigned] Removed Reference MITRE https://oligosecurity.webflow.io/blog/more-models-more-probllms -
CVE Received by [email protected]
Oct. 31, 2024
Action Type Old Value New Value Added Description An issue was discovered in Ollama before 0.1.46. An attacker can use two HTTP requests to upload a malformed GGUF file containing just 4 bytes starting with the GGUF custom magic header. By leveraging a custom Modelfile that includes a FROM statement pointing to the attacker-controlled blob file, the attacker can crash the application through the CreateModel route, leading to a segmentation fault (signal SIGSEGV: segmentation violation). Added Reference MITRE https://github.com/ollama/ollama/compare/v0.1.45...v0.1.46#diff-782c2737eecfa83b7cb46a77c8bdaf40023e7067baccd4f806ac5517b4563131L417 [No types assigned] Added Reference MITRE https://oligosecurity.webflow.io/blog/more-models-more-probllms [No types assigned]
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2024-39720 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2024-39720
weaknesses.