Server crash via crafted GGUF model
Published Mar 20, 2025 · Updated Mar 20, 2025
Out-of-bounds read in Ollama 0.3.14 and earlier allows remote attackers to crash the server by supplying a crafted GGUF model. The GGUF parser in gguf.go reads beyond a buffer boundary while processing attacker-controlled model data. An attacker must make the server process the model; successful exploitation terminates the serving process and interrupts inference requests.
Summary
What happened
Out-of-bounds read in Ollama 0.3.14 and earlier allows remote attackers to crash the server by supplying a crafted GGUF model. The GGUF parser in gguf.go reads beyond a buffer boundary while processing attacker-controlled model data. An attacker must make the server process the model; successful exploitation terminates the serving process and interrupts inference requests.
The record
- CVE
- CVE-2024-12055
- Published
- Mar 20, 2025
- Updated
- Mar 20, 2025
- Vendor
- Ollama
- Product
- Ollama
- Classifications
- CWE-125, T1499
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 20, 2025CVE publishedPublication date reported by the CVE source.
- Mar 20, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=unspecified <=latest
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Public exploit references
- Huntr crafted-GGUF denial-of-service proof of conceptproof of concept · unverified
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo