Information Disclosure in vllm (CVE-2026-105752)
Summary
Vulnerability in vllm (CVE-2026-105752). Risk of unauthorized operations or information disclosure. Exploitable via POST /v1/responses. Mitigation: upgrade to 0.30.0 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 tool-continuation re-submission has omitted the salt.
Summary
On the GPT-OSS "Harmony" path (POST /v1/responses), a request that uses a built-in or MCP tool runs as a multi-turn loop: after each tool call vLLM re-renders the full next-turn Harmony prompt and re-submits it to the engine. Turn 1 correctly carries request.cache_salt, but the tool-continuation re-submission rebuilds the engine input via tokens_input(token_ids) with no cache_salt. The continuation prefix is therefore cached in the global unsalted namespace even though the caller opted into salting. A second tenant who can guess the low-entropy post-tool history submits the reconstructed continuation (unsalted) and reads exact per-turn cached-token counts from the Responses usage — restoring the prompt-membership oracle that cache_salt is documented to prevent.
Silently dropping a preserved salt after the supported tool workflow is enabled is a broken isolation control: the caller enabled salting and every turn should stay isolated, but continuation turns leak into the shared cache.
This is distinct from [GHSA-4qjh-9fv9-r85r](https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r…
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-2026-105752 has been found in vllm.
Attackers can target a specific entry point like POST /v1/responses over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: 3.1/10.
What to do: upgrade vllm to 0.30.0 or later.
If unsure, ask your IT team or search "vllm CVE-2026-105752" on the vendor's site.
CVE-2026-105752 (vllm) — CWE-200 / CVSS v3 3.1
Attack vector: remote (network-reachable) / no user interaction
Attack surface: POST /v1/responses / vllm / request.cache_salt / cache_salt
Patched: 0.30.0 — 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.
Information disclosure (CWE-200) exists in vllm. Attackers reach the vulnerable code path via POST /v1/responses.
Check the vendor advisory for the affected versions of vllm. Attack surface: POST /v1/responses / vllm / request.cache_salt / cache_salt.
Severity: Low (CVSS 3.1/10). Risk of unauthorized operations or information disclosure.
Update to 0.30.0.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual POST /v1/responses requests with malformed payloads or SQL meta-characters. 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。 -
2Hunt for indicators of compromise detect
grep 'POST /v1/responses' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'アクセスログで
POST /v1/responsesへの異常なリクエスト (不正な認証ヘッダ・SQLメタ文字)を過去 30〜90日分捜索。WAF/SIEM があれば該当パスのアラート発火履歴を確認。 -
3Apply patch patch
Upgrade vllm to 0.30.0ステージング環境で 0.30.0 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と、Step 2 で見つけた異常検知の続報チェックを含めること。
-
4Post-deployment verification verify
Replay attack against POST /v1/responses on staging to confirm patch closes the vector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 Step 2 と同じログクエリでアラート再発が無いか継続監視。