Vulnerability in Ggml (CVE-2026-43632)
Summary
Vulnerability in Ggml (CVE-2026-43632). Successful exploitation can lead to full system takeover.
Original description
The description as published by the source.
llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured.
Source: NIST National Vulnerability Database NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-43632 has been found in Ggml.
Successful exploitation can lead to full system takeover. CVSS score: 8.1/10.
What to do: apply the vendor's official patched release.
If unsure, ask your IT team or search "Ggml CVE-2026-43632" on the vendor's site.
CVE-2026-43632 (Ggml) — CWE-367 / CVSS v3 8.1
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
A vulnerability (CWE-367) exists in Ggml.
Check the vendor advisory for the affected versions of Ggml.
Severity: High (CVSS 8.1/10). Successful exploitation can lead to full system takeover.
Update to the patched release per vendor advisory.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'Ggml' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'Ggml' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
Ggmlを grep し、稼働しているサービス・バージョンを把握する。 -
2Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
Fix status by distribution
Fixed packages published by each distribution for this CVE
- Debian DEBIAN-CVE-2026-43632 llama.cpp
- Ubuntu UBUNTU-CVE-2026-43632 llama.cpp
References
- patch disclosure@vulncheck.com
- patch disclosure@vulncheck.com
- web nvd.nist.gov
- web github.com