Vulnerability in vllm (CVE-2026-105753)
Summary
Vulnerability in vllm (CVE-2026-105753). Risk of unauthorized operations or information disclosure. Exploitable via vllm. Mitigation: upgrade to 0.28.0 or later.
Original description
The description as published by the source.
Affected
- Ecosystem / package: pip /
vllm - Affected versions: vLLM ≤ 0.25.1 (confirmed on 0.25.1, commit
752a3a504485). The lower bound predates 0.25.1; maintainers can confirm how far back the mirrored sender/receiver cache protocol reaches.
Summary
vLLM's default multimodal cache (mm_processor_cache_type="lru") mirrors state across two processes: the frontend (P0) holds only metadata (MultiModalProcessorSenderCache) while the engine core (P1) holds the real payload (MultiModalReceiverCache). The design invariant is that get_and_update() runs on P0 and P1 in lockstep for every request, so eviction order stays mirrored and P0 can answer "is this cached in P1?" without talking to P1.
That invariant breaks when a request is rejected after P0 has rendered and hashed the multimodal input (populating the P0 cache) but before P1 receives the item — for example, an oversized chat prompt rejected on max_model_len after rendering. P0 now believes the media is cached while P1 never got it. A later request reusing the same media hash gets a P0 hit, so P0 sends None instead of the payload, and P1 — which has nothing cached — trips assert mm_item is not None, f"Expected a cached item for {mm_hash=}".
This is a remotely reachable, request-controlled cache-mirroring desync on the standard multimodal inference path. It requires only the default cache configur…
Source: NIST National Vulnerability Database NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-105753 has been found in vllm.
Attackers can target a specific entry point like vllm over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: 6.5/10.
What to do: upgrade vllm to 0.28.0 or later.
If unsure, ask your IT team or search "vllm CVE-2026-105753" on the vendor's site.
CVE-2026-105753 (vllm) — CWE-617 / CVSS v3 6.5
Attack vector: remote (network-reachable) / no user interaction
Attack surface: vllm / MultiModalProcessorSenderCache / MultiModalReceiverCache / max_model_len
Patched: 0.28.0 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
A vulnerability (CWE-617) exists in vllm. Attackers reach the vulnerable code path via vllm.
Check the vendor advisory for the affected versions of vllm. Attack surface: vllm / MultiModalProcessorSenderCache / MultiModalReceiverCache / max_model_len.
Severity: Medium (CVSS 6.5/10). Risk of unauthorized operations or information disclosure.
Update to 0.28.0.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'vllm' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'vllm' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
vllmを grep し、稼働しているサービス・バージョンを把握する。 -
2Apply patch patch
Upgrade vllm to 0.28.0ステージング環境で 0.28.0 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。
-
3Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。