Summary
Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um einen Denial of Service Angriff durchzuführen.
Product
Open Source vLLM ist eine Open-Source-Bibliothek für schnelle und effiziente Inferenz von Large Language Models (LLMs).
Vulnerabilities 3
-
Medium 6.5
vLLM 0.19.0 before 0.24.0 Audio Decompression Bomb DoS via Chat Completions
vLLM from 0.19.0 before 0.24.0 contains a decompression bomb vulnerability because the AudioMediaIO multimodal path calls load_audio without the max_duration_s decoded-duration limit. Authenticated attackers can send small compressed audio via input_audio or …
-
Medium 6.5
vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids
vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with inv…
-
Medium 5.9
vLLM 0.22.0 before 0.24.0 Denial of Service via Rust gRPC Generate
vLLM from 0.22.0 before 0.24.0 contains an improper input validation vulnerability in the Rust gRPC Generate and GenerateStream service that forwards unchecked prompt token IDs to EngineCore. Attackers can submit requests with out-of-vocabulary prompt.token_i…
Revision history
-
#1
Initiale Fassung
References
-
Red Hat Bugtracker 2560391 vom 2026-10-25
https://bugzilla.redhat.com/show_bug.cgi?id=2560391
-
Red Hat Bugtracker 2560405 vom 2026-10-25
https://bugzilla.redhat.com/show_bug.cgi?id=2560405
-
Red Hat Bugtracker 2560417 vom 2026-10-25
https://bugzilla.redhat.com/show_bug.cgi?id=2560417