UTC
High

Cross-tenant DoS via uninitialized LogprobsTensors with prompt_logprobs

GHSA-rhcx-5729-88vg · published 2026-10-09

Severity
High
CVSS score
7.7
Chance of exploitation (EPSS)
No CVE
Fixed in
0.31.0
What it is

Remote-trigger crash of EngineCore on a single malformed request. Scope change: the crash kills every in-flight request on the engine, not just the offender's. Co-tenant traffic and in-progress batches are dropped. Trivial to trigger: warm a prefix (or rely on natural cache reuse), then send a request with prompt_logprobs set. Repeatable as a kill-loop. Highest real-world exposure: lm-eval-harness multiple-choice workloads (MMLU, ARC, HellaSwag, BBH, PIQA) against vLLM + LMCache. MC tasks require prompt_logprobs by definition and share per-subject prefixes by construction; item 2 of any subject is a guaranteed crash on a connector-equipped server.

What to do

Upgrade vllm to 0.31.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

Replace torch.empty() with torch.zeros() for token IDs and torch.full(-inf) for logprobs in LogprobsTensors.empty_cpu(). Zero is a valid token ID that decodes safely; -inf is the correct "not computed" sentinel and matches the existing convention for out-of-top-k positions. All non-connector code paths overwrite every position, so the initial values are dead writes in the common case — no behavior change for any previously-working code path. The upstream commit should carry a Fixes: trailer pointing at the regression commit, to let maintainers triage backports automatically:

If you cannot upgrade yet

Until the patch is deployed, any one of the following mitigates the issue: Disable KV connectors on the affected engine (drop --kv-transfer-config and any kv_transfer_config setting). Local prefix caching is unaffected and remains available. Strip prompt_logprobs, logprobs, and echo from inbound requests at an API gateway or middleware in front of vLLM. These are the only request-level switches that reach the crash path. Apply the one-line patch above (torch.empty → torch.zeros / torch.full(-inf) in vllm/v1/outputs.py). No new dependencies, no behavior change on any non-connector path.

Affected
PackageRegistryAffectedFixed in
vllmPyPI>= v0.8.5, < 0.31.00.31.0

The impact, patch and workaround text comes from the advisory, shortened (published by vLLM). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].