Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

github логотип

GHSA-78fp-cf4h-g36p

Опубликовано: 20 июн. 2026
Источник: github
Github: Не прошло ревью
CVSS4: 8.7
CVSS3: 8.8

Описание

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.

EPSS

Процентиль: 28%
0.00352
Низкий

8.7 High

CVSS4

8.8 High

CVSS3

Дефекты

CWE-20
CWE-787

Связанные уязвимости

CVSS3: 8.8
redhat
около 1 месяца назад

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.

CVSS3: 8.8
nvd
около 1 месяца назад

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.

CVSS3: 8.8
debian
около 1 месяца назад

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validat ...

EPSS

Процентиль: 28%
0.00352
Низкий

8.7 High

CVSS4

8.8 High

CVSS3

Дефекты

CWE-20
CWE-787