CyberRota Analysis
AI-GeneratedThe vLLM inference and serving engine for large language models is vulnerable due to improper handling of user-supplied data in the /inference/v1/generate endpoint, which can lead to denial of service or cache poisoning attacks. Attackers can exploit this vulnerability to manipulate the model's behavior or disrupt the shared EngineCore by providing forged inputs. Organizations using versions prior to 0.30.0 should prioritize upgrading to mitigate potential impacts on their model's integrity and availability.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.
Related CVEs
Other vulnerabilities affecting the same vendor(s)