k2-fsa sherpa-onnx up to 1.13.8 Offline Transducer Greedy Search Decoder offline-transducer-greedy-search-decoder.cc Decode vocab_size buffer overflow

Summaryinfo

A vulnerability was found in k2-fsa sherpa-onnx up to 1.13.8. It has been rated as critical. Impacted is the function OfflineTransducerGreedySearchDecoder::Decode of the file sherpa-onnx/csrc/offline-transducer-greedy-search-decoder.cc of the component Offline Transducer Greedy Search Decoder. This manipulation of the argument vocab_size causes buffer overflow. This vulnerability appears as CVE-2026-108954. The attack may be initiated remotely. In addition, an exploit is available. If only official model packs are used and they always keep metadata consistent with the joiner, the bug may not be reachable in normal supported usage. However, from a security and robustness standpoint, the code still contains the vulnerability because it trusts unvalidated model metadata and can be triggered by a malformed or tampered model pack.

Detailsinfo

A vulnerability classified as critical was found in k2-fsa sherpa-onnx up to 1.13.8. Affected by this vulnerability is the function OfflineTransducerGreedySearchDecoder::Decode of the file sherpa-onnx/csrc/offline-transducer-greedy-search-decoder.cc of the component Offline Transducer Greedy Search Decoder. The manipulation of the argument vocab_size with an unknown input leads to a buffer overflow vulnerability. The CWE definition for the vulnerability is CWE-120. The product copies an input buffer to an output buffer without verifying that the size of the input buffer is less than the size of the output buffer, leading to a buffer overflow. As an impact it is known to affect confidentiality, integrity, and availability.

The advisory is shared at github.com. This vulnerability is known as CVE-2026-108954. The exploitation appears to be easy. The attack can be launched remotely. The exploitation doesn't need any form of authentication. It demands that the victim is doing some kind of user interaction. Technical details and also a public exploit are known.

It is possible to download the exploit at github.com. It is declared as proof-of-concept. If only official model packs are used and they always keep metadata consistent with the joiner, the bug may not be reachable in normal supported usage. However, from a security and robustness standpoint, the code still contains the vulnerability because it trusts unvalidated model metadata and can be triggered by a malformed or tampered model pack.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Productinfo

Vendor

• k2-fsa

Name

• sherpa-onnx

Version

• 1.13.0
• 1.13.1
• 1.13.2
• 1.13.3
• 1.13.4
• 1.13.5
• 1.13.6
• 1.13.7
• 1.13.8

Website

• Product: https://github.com/k2-fsa/sherpa-onnx/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Submitinfo

Accepted

• Submit #997824: k2-fsa sherpa-onnx up to 1.13.8 (master commit 040afe360a38e25daaa325ce8889abf93ea02609 also affected) Heap-based Buffer Overflow (by Dem0)

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Discussion