Security Digest · Vulnerability record
CVE-2026-7482: Ollama heap out-of-bounds read in GGUF tensor parsing leaks server process memory to unauthenticated remote attackers
Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader.
CVSS 8.8 High EPSS 0.7% · p53 Check exposure
Should you act?
Normal patch cycle
No exploitation signal; fix it in your next routine update if you are affected. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- No confirmed exploitation. It is not in CISA’s KEV catalog and CISA’s SSVC assessment records no known exploitation. That can change quickly after a public write-up; re-check if you are affected.
- EPSS 0.7%, percentile 53: FIRST’s model estimates a 0.7% chance of exploitation activity in the next 30 days, higher than 53% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Editorial verdict: Check exposure. Bleeding Llama: Unauthenticated Memory Leak in Ollama — A laptop running Ollama on its default localhost binding is not reachable; a server you exposed with OLLAMA_HOST=0.0.0.0 or a published Docker port is, and it should be updated and its secrets rotated.
What it is
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 OLLAMAHOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed).
Weakness type: CWE-125.
Product: ollama ollama · Assigned by: Echo · Published: 2026-05-04
Affected and fixed versions
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| ollama | ollama | < 0.17.1 |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| Echo | 3.1 | 9.1 Critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H |
| Echo | 4.0 | 8.8 High | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:H/SC:N/SI:N/SA:N/AU:Y/R:A/V:D/RE:L/U:Red |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Attack requirements: none
- Privileges required: none (no login)
- User interaction: none
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation none, automatable yes, technical impact total.
- FIRST EPSS (model of 2026-10-21): 0.71% probability of exploitation activity in the next 30 days; percentile 53.
Timeline
- — erroneo.us brief: Bleeding Llama: Unauthenticated Memory Leak in Ollama
- — CVE record last updated
- — CVE record published by Echo
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vendor and project advisories, patches
- ollama/ollama PR #14406 — ggml: ensure tensor size is valid (fix) github.com
- Fix commit 88d57d0 github.com
- ollama v0.17.1 release notes github.com
Vulnerability records
- CVE.org record CVE-2026-7482 cve.org
- NVD entry CVE-2026-7482 nvd.nist.gov