CVE-2026-43632Disclosure(ggml / llama.cpp)

LOWCVSS 9.2 · CRITICAL

Signal is active with 1 mentions in latest observed window

Immediate actions

Track advisory updates for patch or workaround availability

Recommended action window: Monitor and triage in normal cycle

NVD description

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.

ggml CVEs Back to dashboard

0.0/ 10 priority

Sources & remediation

Patch / fix

Weakness type (CWE)

CWE-367CWE-416

Priority

LOW

Exploitation

NONE

PoC

NONE

Patch

AVAILABLE

Momentum

NONE

Are you affected?

If you run products in this scope, you should treat this CVE as relevant to your environment.

llama.cpp

Threat summary

1 mentions across 1 observed day

What's happening

Technical details provided in 1 signal
Disclosure: 1 classified signal
1 total mentions across 1 day

Affected systems

Vendors

ggml

Products

llama.cpp

Deep dive

Activity timeline1 mentions / 1d

Signal classification1 categories

Disclosure

1100.0%

Full discourse1 post

CyberSignal | Cybersecurity News@XQOPTRX46d
Disclosure
🤖 Critical llama.cpp server use-after-free disclosed CVE-2026-43632 — Critical Several llama.cpp server tokenization endpoints can hit a race condition causing use-after-free memory access. Impact includes crashes and potentially code execution under affected configurations. 🔎 Source: Tenable / CVE #LlamaCPP #LLM #AISecurity #CVE #CyberSecurity
Post summary
A critical use‑after‑free vulnerability has been disclosed in certain llama.cpp server tokenization endpoints, potentially causing crashes or code execution.
0000077
34 followersView on X

CPE platform detail1 entries

Part:

Vendor:

Product:

Version:

Target SW:

Target HW:

1 of 1 entries

Part	Vendor	Product	Version	Target SW	Target HW
App	ggml	llama.cpp	-	-	-

Explore more

Back to dashboard ggml CVEs llama.cpp vulnerabilities