SUSE CVE-2026-93989

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

PYSEC-2026-4000

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

PYSEC-0000-CVE-2026-93989

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

PYSEC-2026-4000

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

CVE-2026-93989 vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words

vLLM through 0.29.0 fails to properly validate badwords token indices against the model's generation output width in SamplingParams.updatefromtokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to...

CVE-2026-93989

The vLLM inference and serving engine (through version 0.29.0 ) is vulnerable to an Improper Validation of Array Index in the SamplingParams.update_from_tokenizer() function. A remote authenticated attacker can supply out-of-bounds bad_words token indices that fail to be validated against the mod...

PT-2026-102786

vLLM through 0.29.0 fails to properly validate bad words token indices against the model's generation output width in SamplingParams.update from tokenizer. Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests...

PT-2026-95873

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.29.1 Description The software fails to properly validate bad words token indices against the model's generation output width within the SamplingParams.update from tokenizer function. This allows attackers to provide...