SSRF (Server-Side Request Forgery) in github.com/mudler/LocalAI (CVE-2026-59707)
Summary
SSRF in github.com/mudler/LocalAI (CVE-2026-59707). Confidential information can be exposed externally. Exploitable via POST /models/apply. Mitigation: upgrade to 1.40.1-0.20260703213242-2cbb3c96b34d or later.
Original description
The description as published by the source.
LocalAI contains an unauthenticated server-side request forgery vulnerability in the POST /models/apply endpoint that allows attackers to fetch arbitrary internal URLs. The endpoint passes unsanitized gallery URL fields directly to gallery.GetGalleryConfigFromURLWithContext without proper validation, enabling attackers to force the server to issue HTTP GET requests to private and loopback ranges with partial response content leaked through error messages.
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-2026-59707 has been found in github.com/mudler/LocalAI.
Attackers can target a specific entry point like POST /models/apply over the network to misuse the product.
Confidential information can be exposed externally. CVSS score: 8.6/10.
What to do: upgrade github.com/mudler/LocalAI to 1.40.1-0.20260703213242-2cbb3c96b34d or later.
If unsure, ask your IT team or search "github.com/mudler/LocalAI CVE-2026-59707" on the vendor's site.
CVE-2026-59707 (github.com/mudler/LocalAI) — CWE-918 / CVSS v3 8.6
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: POST /models/apply
Patched: 1.40.1-0.20260703213242-2cbb3c96b34d — 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.
SSRF (CWE-918) exists in github.com/mudler/LocalAI. Attackers reach the vulnerable code path via POST /models/apply without authentication.
Check the vendor advisory for the affected versions of github.com/mudler/LocalAI. Attack surface: POST /models/apply.
Severity: High (CVSS 8.6/10). Confidential information can be exposed externally.
Update to 1.40.1-0.20260703213242-2cbb3c96b34d.
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 /models/apply requests with malformed payloads or SQL meta-characters. Run grep -r 'github.com/mudler/LocalAI' . 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 'github.com/mudler/LocalAI' . | 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
github.com/mudler/LocalAI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 /models/apply' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'アクセスログで
POST /models/apply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 github.com/mudler/LocalAI to 1.40.1-0.20260703213242-2cbb3c96b34dステージング環境で 1.40.1-0.20260703213242-2cbb3c96b34d 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 /models/apply 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 nvd.nist.gov
- advisory github.com
- package github.com
- web github.com
- web github.com
- web vulncheck.com