Threat Intelligence / CVE / CVE-2026-7482

CVE-2026-7482

CVSS 9.1 (CRITICAL) · EPSS 1.0% · Priority 6.9/10 · Published 2026-05-04

As of 2026-05-04, CVE-2026-7482 is a CVSS 9.1 (CRITICAL-severity) vulnerability. EPSS exploitation probability 1.0%. Threadlinqs Intelligence tracks 1 threat exploiting it.

Last updated: 2026-05-04

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).

CVSS v3 vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H

Weaknesses (CWE)

CWE-125

Affected packages

go:github.com/ollama/ollama — patched in 0.17.1

Threats tracking this CVE

AI Compute Hijacking: Stolen Ollama Server Wired Into Autonomous "VAPT" Exploit Pipeline (Sysdig) — HIGH

References

Full detection coverage & IOCs for threats exploiting CVE-2026-7482 are available via the Threadlinqs MCP server (Purple tier). View plans →

← all vulnerabilities · Markdown version · Threadlinqs Intelligence

Enriched from CVE.org, NVD (this product uses the NVD API but is not endorsed or certified by the NVD), FIRST EPSS, CISA KEV, and GitHub Security Advisories.