CVE-2026-93989
What it is
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.
At a glance
- Exploitability
- Can be exploited over the network with a low-privilege account. Limited direct impact.
- Exploit odds
- 0.2% chance of exploitation in the next 30 days (EPSS).
- Fix
- A patch, advisory or fixed version is referenced. Upgrade or apply it.
Timeline
- PublishedDisclosed publicly on CVE.org and NVD
- Last updatedMost recent change to the record
Why it ranks here
- Exploited in the wild: no, CISA does not list it.
- Exploit odds: 0.2% in the next 30 days (EPSS).
- Severity: 2.3 LOW (CVSS).
- Fix: a patch or advisory is linked.
Details
- Published
- Last modified
- Exploit probability
- 0.2% · EPSS, next 30 days
- Weakness
- CWE-129
- Record status
- Analyzed
Affected
- Vllm ≤ 0.29.0
Attack profile CVSS 4.0 · 2.3
- Attack vector
- Network
- Complexity
- High
- Attack requirements
- Present
- Privileges needed
- Low
- User interaction
- None
- Confidentiality
- None
- Integrity
- Low
- Availability
- None
Raw vector
CVSS:4.0/AV:N/AC:H/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Is it in your code?
Hand this to your coding agent. It searches your project for the affected products and checks versions. Nothing leaves your machine.
Read https://cve-list.com/agent/cve/CVE-2026-93989.md and follow it. Check whether this project is affected by CVE-2026-93989. Read only. Don't change anything and don't upload my code. Tell me yes, no or not sure, with the file as proof.
Fix and advisories
References
- https://github.com/vllm-project/vllm
- https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/sampling_params.py#L694-L753
- https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/v1/worker/gpu/sample/bad_words.py
- https://github.com/vllm-project/vllm/pull/48824
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-cross-request-logits-corruption-via-bad-words