CVE-2026-93989
vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words
Description
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 to return incorrect tokens.
No summary for this CVE yet.
CVSS Vector Breakdown
Exploitability
AV:NAttack VectorNetwork
AC:HAttack ComplexityHigh
PR:LPrivileges RequiredLow
UI:NUser InteractionNone
Scope
S:UScopeUnchanged
Impact
C:NConfidentialityNone
I:LIntegrityLow
A:NAvailabilityNone
Weaknesses
Affected Products
vllm-project
oss-projectaka vllm-project/vllm, vllm
Exploitability
No known exploits, KEV entries, or remediation guidance available for this vulnerability yet.
References
https://github.com/vllm-project/vllm/pull/48824
github.com
https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/v1/worker/gpu/sample/bad_words.py
github.com
https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/sampling_params.py#L694-L753
github.com
and 2 more references View all →
Unlock Complete Vulnerability Intelligence
Get the full picture for CVE-2026-93989 and every CVE in our database. Create a free account — no credit card required.
Create Free AccountPlain-language analysis
Impact assessment and exploitation scenario in plain English
Attack graph visualization
Interactive attack path and kill chain mapping
Exploit details & PoC links
ExploitDB, Metasploit, GitHub PoCs with direct links
Nuclei scanner templates
Ready-to-use vulnerability scanner templates
Full remediation guide
Patch instructions, workarounds, and compliance impact
Interactive AI chat
Ask questions about this vulnerability in natural language
Related vulnerabilities
Semantically similar CVEs and attack patterns
REST API & MCP access
Integrate vulnerability data into your workflows