← Back
CVE-2026-28277
Unsafe Deserialization in langgraph (CVE-2026-28277)
Summary
vulnerability in langgraph (CVE-2026-28277). Successful exploitation can lead to full system takeover. Exploitable via ``LANGGRAPH_STRICT_MSGPACK``. Mitigation: upgrade to `1.0.10` or later.
AI summary snake-internal / snake-material-v2
A vulnerability tracked as **CVE-2026-28277** has been found in langgraph.
Attackers can target a specific entry point like ``LANGGRAPH_STRICT_MSGPACK`` over the network to misuse the product.
Successful exploitation can lead to full system takeover. CVSS score: ?/10.
What to do: upgrade langgraph to **1.0.10** or later.
If unsure, ask your IT team or search "langgraph CVE-2026-28277" on the vendor's site.
CVE-2026-28277 (langgraph) — CWE-502 /
Attack vector: adjacent-network / no user interaction
Attack surface: `LANGGRAPH_STRICT_MSGPACK` / `true` / `yes` / `allowed_msgpack_modules`
Patched: `1.0.10` — 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
**unsafe deserialization** (CWE-502) exists in langgraph. Attackers reach the vulnerable code path via ``LANGGRAPH_STRICT_MSGPACK`` without authentication.
📍 Affected scope
langgraph — . Attack surface: `LANGGRAPH_STRICT_MSGPACK` / `true` / `yes` / `allowed_msgpack_modules`.
🔥 Severity
Severity: ?. Successful exploitation can lead to full system takeover
🔧 How to fix
Update to **1.0.10**.
🛡️ 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 'langgraph' .` 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 'langgraph' . | 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 `langgraph` 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 langgraph to 1.0.10ステージング環境で 1.0.10 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
langgraph
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"1.0.10"}]}]
pip
langgraph
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"1.0.10"}]}]
References
- advisory https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/28xxx/CVE-2026-28277.json
- advisory https://nvd.nist.gov/vuln/detail/CVE-2026-28277
- package https://github.com/langchain-ai/langgraph
- web https://github.com/langchain-ai/langgraph/security/advisories/GHSA-g48c-2wqr-h844
- web https://github.com/pypa/advisory-database/tree/main/vulns/langgraph/PYSEC-2026-83.yaml
- web https://github.com/advisories/GHSA-g48c-2wqr-h844