← Back
CVE-2026-40087
Vulnerability in langchain-core (CVE-2026-40087)
Summary
vulnerability in langchain-core (CVE-2026-40087). Risk of unauthorized operations or information disclosure. Exploitable via ``PromptTemplate``. Mitigation: upgrade to `1.2.28` or later.
AI summary snake-internal / snake-material-v2
A vulnerability tracked as **CVE-2026-40087** has been found in langchain-core.
Attackers can target a specific entry point like ``PromptTemplate`` over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: ?/10.
What to do: upgrade langchain-core to **1.2.28** or later.
If unsure, ask your IT team or search "langchain-core CVE-2026-40087" on the vendor's site.
CVE-2026-40087 (langchain-core) — CWE-1336 /
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: `PromptTemplate` / `DictPromptTemplate` / `ImagePromptTemplate`
Patched: `1.2.28` — 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.
❓ What is the problem
**A vulnerability** (CWE-1336) exists in langchain-core. Attackers reach the vulnerable code path via ``PromptTemplate`` without authentication.
📍 Affected scope
langchain-core — . Attack surface: `PromptTemplate` / `DictPromptTemplate` / `ImagePromptTemplate`.
🔥 Severity
Severity: ?. Risk of unauthorized operations or information disclosure
🔧 How to fix
Update to **1.2.28**.
🛡️ 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 request patterns matching this CVE's known IOCs. Run `grep -r 'langchain-core' .` 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
-
1Identify exposure identify
grep -r 'langchain-core' . | 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 `langchain-core` を grep し、稼働しているサービス・バージョンを把握する。
-
6Apply patch patch
Upgrade langchain-core to 1.2.28ステージング環境で 1.2.28 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 3 で見つけた異常検知の続報チェックを含めること。
-
7Post-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 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
langchain-core
[{"type":"ECOSYSTEM","events":[{"introduced":"1.0.0a1"},{"fixed":"1.2.28"}]}]
References
- advisory https://nvd.nist.gov/vuln/detail/CVE-2026-40087
- advisory https://github.com/advisories/GHSA-926x-3r5x-gfhw
- package https://github.com/langchain-ai/langchain
- package https://pypi.org/project/langchain-core
- web https://github.com/langchain-ai/langchain/security/advisories/GHSA-926x-3r5x-gfhw
- web https://github.com/langchain-ai/langchain/pull/36612
- web https://github.com/langchain-ai/langchain/pull/36613
- web https://github.com/langchain-ai/langchain/commit/6bab0ba3c12328008ddca3e0d54ff5a6151cd27b
- web https://github.com/langchain-ai/langchain/commit/af2ed47c6f008cdd551f3c0d87db3774c8dfe258
- web https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.84
- web https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.28