Out-of-bounds Read in Ollama
CVE-2026-7482
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).
Vulnerability class: Buffer Overflow
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.1 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H.
EPSS exploit prediction
EPSS 0.071, 94.3th percentile (scored ); up from 0.007 30 days earlier. About EPSS.
EPSS over last 30 days · oldest: 0.007 · newest: 0.071 · change: +0.064
Affected products
- Ollama — versions 0
Weakness classification (CWE)
Public exploits and proof-of-concept code
3 public repositories with exploit or proof-of-concept code for this CVE:
- 0x0OZ/CVE-2026-7482-PoC (7 stars, last pushed 2026-05-05): 1day vuln research I guess
- szybnev/CVE-2026-7482 (1 star, last pushed 2026-05-07): Ollama CVE-2026-7482 Heap OOB read reproduction and black-box impact notes
- kaleth4/CVE-2026-7482 (last pushed 2026-05-10)
References
- github.com/ollama/ollama/commit/88d57d0483cca907e0b23a968c83627a20b21047 (Patch, patch)
- github.com/ollama/ollama/pull/14406 (Patch, patch, Issue Tracking)
- github.com/ollama/ollama/releases/tag/v0.17.1 (release-notes, Release Notes)
This CVE has public exploit evidence. See the latest CVEs with public exploits.