Public mode

No access to your tenant or devices. Every item links to its source. What this means

Sources need attention Customize Public modeDiscuss ChangeIntel on Discord

ollama · Vulnerability

CVSS 3.1 9.1 CRITICALCVSS 4.0 8.8 HIGHEUVD CVSS 4.0 8.8 CVSS 4.0 · abd028dc-c042-4c4d-9749-38d0f850af89 · Secondary 8.8 HIGHCVSS 3.1 · abd028dc-c042-4c4d-9749-38d0f850af89 · Secondary 9.1 CRITICALCVSS_V3 CVSS_V4 Publisher rating HIGHFixed by github.com/ollama/ollama 0.17.1osv · severity unknownFixed by github.com/ollama/ollama 0.17.1KEV status unknown

cve-program · CVE-2026-7482

Published

Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may include environment variables, API keys, system prompts, and concurrent users' conversation data, and can be exfiltrated by uploading the resulting model artifact through the /api/push endpoint to an attacker-controlled registry. The /api/create and /api/push endpoints have no authentication in the upstream distribution. Default deployments bind to 127.0.0.1, but the documented OLLAMA_HOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed).

Read the publisher's advisory

euvd · EUVD-2026-26949

Published

Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may include environment variables, API keys, system prompts, and concurrent users' conversation data, and can be exfiltrated by uploading the resulting model artifact through the /api/push endpoint to an attacker-controlled registry. The /api/create and /api/push endpoints have no authentication in the upstream distribution. Default deployments bind to 127.0.0.1, but the documented OLLAMA_HOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed).

Read the publisher's advisory

nvd · CVE-2026-7482

Published

Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may include environment variables, API keys, system prompts, and concurrent users' conversation data, and can be exfiltrated by uploading the resulting model artifact through the /api/push endpoint to an attacker-controlled registry. The /api/create and /api/push endpoints have no authentication in the upstream distribution. Default deployments bind to 127.0.0.1, but the documented OLLAMA_HOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed).

Read the publisher's advisory

osv · GHSA-x8qc-fggm-mpqg

Published

Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may include environment variables, API keys, system prompts, and concurrent users' conversation data, and can be exfiltrated by uploading the resulting model artifact through the /api/push endpoint to an attacker-controlled registry. The /api/create and /api/push endpoints have no authentication in the upstream distribution. Default deployments bind to 127.0.0.1, but the documented OLLAMA_HOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed).

Read the publisher's advisory

osv · GO-2026-5748

Published

Ollama is vulnerable to a heap out-of-bounds read in its GGUF model loader. A specially crafted GGUF file can cause the loader to read beyond the allocated heap buffer, potentially leading to a denial of service (crash).

Read the publisher's advisory

Affected versions, risk and source history

Related advisories and sources

Related changes

Linked by CVE identifier
ChangeIntel

An IT change radar: releases, security, known issues, retirements, documentation changes, and service status from public sources. Every item links to supporting evidence; dates and statuses can change after they are read.

Sources read 16 Nov 02:37 UTC · 274 of 275 readable · 258 fully read · 11 waiting for GitHub's hourly limit · documentation 444/469 current