Sign in Sign up
JA · EN · FR
SecPulse
← Back
CVE-2026-33626

SSRF (Server-Side Request Forgery) in lmdeploy (CVE-2026-33626)

Summary

SSRF in lmdeploy (CVE-2026-33626). Confidential information can be exposed externally. Exploitable via `POST /v1/chat/completions`.

AI summary snake-internal / snake-material-v2

A vulnerability tracked as **CVE-2026-33626** has been found in lmdeploy. Attackers can target a specific entry point like `POST /v1/chat/completions` over the network to misuse the product. Confidential information can be exposed externally. CVSS score: ?/10. What to do: apply the vendor's official patched release. If unsure, ask your IT team or search "lmdeploy CVE-2026-33626" on the vendor's site.
CVE-2026-33626 (lmdeploy) — CWE-918 / Attack vector: remote (network-reachable) / unauthenticated / no user interaction Attack surface: POST /v1/chat/completions / `image_url` 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.
❓ What is the problem
**SSRF** (CWE-918) exists in lmdeploy. Attackers reach the vulnerable code path via `POST /v1/chat/completions` without authentication.
📍 Affected scope
lmdeploy — . Attack surface: POST /v1/chat/completions / `image_url`.
🔥 Severity
Severity: ?. Confidential information can be exposed externally
🔧 How to fix
Update to the patched release per vendor advisory.
🛡️ Workaround
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
🔍 Detection
Search webserver/proxy logs for unusual `POST /v1/chat/completions` requests with malformed payloads or SQL meta-characters. Run `grep -r 'lmdeploy' .` against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.

Response Actions (7 steps)

Concrete steps and command examples for SOC/SRE teams to execute in order

  1. 1
    Identify exposure identify 
    grep -r 'lmdeploy' . | 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 `lmdeploy` を grep し、稼働しているサービス・バージョンを把握する。

  2. 3
    Hunt for indicators of compromise detect 
    grep 'POST /v1/chat/completions' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'

    アクセスログで `POST /v1/chat/completions` 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。

  3. 7
    Post-deployment verification verify 
    Replay attack against POST /v1/chat/completions 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 3 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

PyPI lmdeploy
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"0.12.2"}]}]

References

🍪 About cookies

We use cookies to keep you logged in, remember your language, and improve the service.

Details →