Lucene search
K

6 matches found

Chainguard
Chainguard
added 2025/03/22 10:12 a.m.26 views

CVE-2025-29783 vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm, py3.10-vllm-cuda-11.8...

9CVSS7AI score0.0082EPSS
Exploits0
Circl
Circl
added 2025/03/19 4:40 p.m.6 views

CVE-2025-29783

creationtimestamp| type| source ---|---|--- 2025-03-19 16:40:23+00:00| seen| https://bsky.app/profile/cyberalerts.bsky.social/post/3lkqmqrrvxt2p 2025-03-19 17:27:23+00:00| seen| https://infosec.exchange/users/cR0w/statuses/114190269963714967 2025-03-19 17:30:32+00:00| published-proof-of-concept|...

9CVSS8.6AI score0.0082EPSS
Exploits0References9
NVD
NVD
added 2025/03/19 4:15 p.m.15 views

CVE-2025-29783

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code...

9CVSS0.0082EPSS
Exploits0References3
CVE
CVE
added 2025/03/19 3:33 p.m.285 views

CVE-2025-29783

CVE-2025-29783 affects vLLM when Mooncake is configured for KV distribution across distributed hosts. The root cause is unsafe deserialization via pickle in the mooncake_pipe path exposed over ZMQ/TCP on all network interfaces, allowing remote code execution on affected distributed hosts. Public ...

9CVSS9.8AI score0.0082EPSS
Exploits0References3Affected Software1
Vulnrichment
Vulnrichment
added 2025/03/19 3:33 p.m.20 views

CVE-2025-29783 vLLM Allows Remote Code Execution via Mooncake Integration

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code...

9CVSS9.8AI score0.0082EPSS
Exploits0References3
Cvelist
Cvelist
added 2025/03/19 3:33 p.m.19 views

CVE-2025-29783 vLLM Allows Remote Code Execution via Mooncake Integration

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code...

9CVSS0.0082EPSS
Exploits0References3
Rows per page
Query Builder