CVE-2026-65315

A flaw was found in Ollama. A remote attacker can exploit an uncontrolled memory allocation vulnerability in the GGUF metadata parser. By supplying a specially crafted GGUF file, an attacker can manipulate length and count fields, leading to excessive memory allocation. This can cause the server ...

SUSE CVE-2026-65315

Ollama HEAD f0078ae contains an uncontrolled memory allocation vulnerability in the GGUF metadata parser that allows remote attackers to crash the server by supplying a crafted GGUF file with attacker-controlled length and count fields in string lengths, tensor dimension counts, and metadata arra...

CVE-2026-65315 Ollama Remote Denial of Service via Attacker-Controlled Allocation in GGUF Metadata Parser

Ollama HEAD f0078ae contains an uncontrolled memory allocation vulnerability in the GGUF metadata parser that allows remote attackers to crash the server by supplying a crafted GGUF file with attacker-controlled length and count fields in string lengths, tensor dimension counts, and metadata arra...

CVE-2026-65315

Technical details about CVE-2026-65315 are not publicly available in the provided documents. Monitor for updates.

CVE-2026-65315

Ollama HEAD f0078ae contains an uncontrolled memory allocation vulnerability in the GGUF metadata parser that allows remote attackers to crash the server by supplying a crafted GGUF file with attacker-controlled length and count fields in string lengths, tensor dimension counts, and metadata arra...

CVE-2026-65315: Memory Allocation with Excessive Size Value

Ollama HEAD f0078ae contains an uncontrolled memory allocation vulnerability in the GGUF metadata parser that allows remote attackers to crash the server by supplying a crafted GGUF file with attacker-controlled length and count fields in string lengths, tensor dimension counts, and metadata arra...

PT-2026-53477

Description llama-cpp-python depends on class Llama in llama.py to load .gguf llama.cpp or Latency Machine Learning Models. The init constructor built in the Llama takes several parameters to configure the loading and running of the model. Other than NUMA, LoRa settings, loading tokenizers, and...

SUSE CVE-2025-66960

An issue in ollama v.0.12.10 allows a remote attacker to cause a denial of service via the fs/ggml/gguf.go, function readGGUFV1String reads a string length from untrusted GGUF metadata...

Improper Handling of Length Parameter Inconsistency

Overview Affected versions of this package are vulnerable to Improper Handling of Length Parameter Inconsistency in readGGUFString. An attacker can cause the service to become unavailable by supplying malicious GGUF metadata. Details Denial of Service DoS describes a family of attacks, all aimed ...

CVE-2025-66960

An issue in ollama v.0.12.10 allows a remote attacker to cause a denial of service via the fs/ggml/gguf.go, function readGGUFV1String reads a string length from untrusted GGUF metadata...

CVE-2025-66960

The Ollama large language model management system is vulnerable to a denial of service (DoS) attack in versions prior to 0.12.10 . The root cause is insufficient validation in the readGGUFV1String() function located in fs/ggml/gguf.go , which reads a string length from untrusted GGUF metadata . A...

PT-2026-3790

Name of the Vulnerable Software and Affected Versions Ollama versions prior to 0.12.10 Description An issue exists in the readGGUFV1String function within the Ollama large language model LLM launch and management system. Insufficient input validation in this function can allow a remote attacker t...

CVE-2025-66960

An issue in ollama v.0.12.10 allows a remote attacker to cause a denial of service via the fs/ggml/gguf.go, function readGGUFV1String reads a string length from untrusted GGUF metadata...