Ggml-org llama.cpp
llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer
llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llm_tokenizer_plamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like <0x-1> whose negative parsed value writes token ids before the bytes_ buffer during model loading, causing crashes or potential code execution.
First public PoC
None yetno public PoC found
Public PoCs00 on GitHub
CVSS8.5high · scored by CNA · CWE-129
CISA KEV
Not listednot known exploited
Affected versions and mitigation
From the CVE record and the vendor's references.Affected
ggml-org llama.cpp
- >= b5899, < b10261
Fixed in b10261
Mitigation
Upgrade llama.cpp to b10261 or later.
References
- Patch github.com/ggml-org/llama.cpp/pull/25969
- Patch github.com/ggml-org/llama.cpp/pull/26511
- Patch github.com/ggml-org/llama.cpp/commit/cf06ad7df…
1 more
- Release notes github.com/ggml-org/llama.cpp/releases/tag/b10…
Timeline
Days relative to CVE publicationNo public PoC found yet; not in CISA KEV.
PoC repositories
Found on GitHub.No PoC repositories found yet.