Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-43632 – Use-After-Free (Remote) – llama.cpp llama-server builds b7492–b9060

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-43632 is a use-after-free vulnerability in the llama.cpp llama-server HTTP server (ggml-org), affecting builds b7492 through b9060. Six tokenization endpoints access the server’s vocabulary object directly on HTTP worker threads, creating a time-of-check-to-time-of-use race that a remote, unauthenticated attacker can trigger. It is rated Critical (CVSS v4.0 9.2).

Technical details

  • Root cause: The /tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens endpoints bypass the task queue and access ctx_server.vocab directly on HTTP worker threads (CWE-416 Use After Free, CWE-367 TOCTOU race condition).
  • Trigger conditions: A race in which the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it; exploitation is associated with the --sleep-idle-seconds option being configured.
  • Attack vector: Network — the affected endpoints are reachable over the HTTP interface without authentication.
  • Impact: Use-after-free with high impact to confidentiality, integrity, and availability.

Affected software

  • llama.cpp (llama-server, ggml-org) builds b7492 through b9060, inclusive.

Severity

  • CVSS v3.1 base score: 8.1 (High) — vector CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H.
  • CVSS v4.0 base score: 9.2 (Critical) — vector CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N.

Mitigation and recommended actions

  • Immediate: No official fixed build was published by the maintainers at time of disclosure. Apply the researcher-provided source patch to affected llama.cpp installations and rebuild.
  • If no patch: The exploit condition is associated with --sleep-idle-seconds; avoid enabling this option. Restrict network access to llama-server so the HTTP endpoints are not exposed to untrusted networks, and place the server behind authenticated, access-controlled proxies.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge