Answer in brief
CVE-2026-43632 records a High severity (CVSS 8.1) vulnerability in llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints. The current sources do not mark it as known exploited. The current feed maps ggml-org/llama.cpp (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 8.1. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps ggml-org/llama.cpp (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| ggml-org/llama.cppgeneric | b7492 | Not reported |
Published upstream
Aug 6, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Aug 6, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Aug 6, 2026
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.
Quoted source text, attributed separately from HOL analysis.
Answer in brief
CVE-2026-43632 records a High severity (CVSS 8.1) vulnerability in llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints. The current sources do not mark it as known exploited. The current feed maps ggml-org/llama.cpp (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 8.1. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps ggml-org/llama.cpp (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| ggml-org/llama.cppgeneric | b7492 | Not reported |
Published upstream
Aug 6, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Aug 6, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Aug 6, 2026
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.
Quoted source text, attributed separately from HOL analysis.