Vulnerability in vllm (CVE-2026-54236)
Summary
Vulnerability in vllm (CVE-2026-54236). Risk of unauthorized operations or information disclosure. Exploitable via POST /v1/messages. Mitigation: upgrade to 0.24.0 or later.
Original description
The description as published by the source.
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo str(exc) directly to clients without calling sanitize_message. The unsanitized sites include the Anthropic API router in vllm/entrypoints/anthropic/api_router.py (the POST /v1/messages and POST /v1/messages/count_tokens handlers), the Server-Sent Events streaming converter in vllm/entrypoints/anthropic/serving.py, and the realtime speech-to-text WebSocket in vllm/entrypoints/speech_to_text/realtime/connection.py. These paths catch the exception inside the route coroutine and construct the JSONResponse themselves, bypassing the sanitizing global FastAPI exception handler, and WebSocket frames do not traverse that handler chain at all. Using the same primitive as the parent issue, an unauthenticated attacker can send malformed image bytes through the Anthropic Messages API image content parts so that PIL.Image.open raises an UnidentifiedImageError whose message contains the BytesIO object repr, leaking the heap memory address verbatim in the error.message field of the response body. This vulnerability is fixed in 0.23.1rc0.
Source: GitHub Security Advisories (Global) 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-2026-54236 has been found in vllm.
Attackers can target a specific entry point like POST /v1/messages over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: 5.3/10.
What to do: upgrade vllm to 0.24.0 or later.
If unsure, ask your IT team or search "vllm CVE-2026-54236" on the vendor's site.
CVE-2026-54236 (vllm) — CWE-532 / CVSS v3 5.3
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: POST /v1/messages / POST /v1/messages/count_tokens / sanitize_message / UnidentifiedImageError
Patched: 0.24.0 — 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-532) exists in vllm. Attackers reach the vulnerable code path via POST /v1/messages without authentication.
Check the vendor advisory for the affected versions of vllm. Attack surface: POST /v1/messages / POST /v1/messages/count_tokens / sanitize_message / UnidentifiedImageError.
Severity: Medium (CVSS 5.3/10). Risk of unauthorized operations or information disclosure.
Update to 0.24.0.
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/messages 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/messages' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'アクセスログで
POST /v1/messages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 0.24.0ステージング環境で 0.24.0 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/messages 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。
Affected packages
References
- advisory github.com
- advisory nvd.nist.gov
- advisory github.com
- patch github.com
- patch github.com
- web github.com
- web github.com
- web github.com
- web pypi.org