UTC

langchain

22 published advisories; version 1.3.9 or later fixes all but 1 of them.

Registry
PyPI
Advisories
22
Latest fix
1.3.9
Exploited in the wild
None listed
Advisories with no fix yet

One advisory has no fixed release in any version yet. What can be done meanwhile:

General guidance from ShieldPi, not a vendor fix

  • Command or code injection. Remove or disable the affected server or tool, or run it in a sandbox with no secrets in its environment.GHSA-fprp-p869-w6q2

Check your machine

Finds langchain in your agent and MCP configs, installed skills, global npm packages, the npx and uvx caches, uv and pipx tools, Claude Code and Cursor. It runs offline and sends nothing anywhere.

pip install "shieldpi>=0.10.0"
shieldpi agent-config . --installed
Downstream in the Official MCP Registry

1 registered MCP server installs an affected version today, by the dependency versions a fresh install resolves.

  • io.github.jahanv01/sec-intelligence-mcplangchain@0.3.30
See the trace →
Malicious lookalikes

Packages reported malicious by OpenSSF whose names imitate langchain. Check that you install langchain itself.

All AI lookalikes →
Provenance

Source: github.com/langchain-ai/langchain, named in the package metadata (not verified)

0 of the last 10 releases of langchain were published with build provenance: a signed record of the repository and commit each was built from, which the registry checks before it accepts the release.

  • 1.5.0
  • 1.4.10
  • 1.4.9
  • 1.4.8
  • 1.4.7
  • 1.4.6
  • 1.4.5
  • 1.4.4
  • 1.4.3
  • 1.4.2

Green: published with provenance. Grey: without.

OpenSSF Scorecard: 5.9 of 10 on 2026-11-16.

No dangerous CI workflows
10/10
CI tokens read-only by default
0/10
Build dependencies pinned
8/10
Branch protection
3/10
Changes reviewed before merge
5/10
Signed releases
0/10
Actively maintained
10/10
Security policy
9/10
Full Scorecard →

Provenance from deps.dev (CC BY 4.0); Scorecard from OpenSSF (CDLA-Permissive-2.0). As of 2026-11-18.

Advisories
AdvisorySeverityAffectedFixed inPublished
LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loadersCVE-2026-55443Medium<= 1.3.81.3.92026-06-16
LangSmith SDK: Public prompt pull deserializes untrusted manifests without trust boundary warningCVE-2026-45134High< 0.3.300.3.302026-05-13
Langchain SQL Injection vulnerabilityCVE-2024-8309Low< 0.2.00.2.02024-10-29
Denial of service in langchain-communityCVE-2024-2965Medium>= 0, < 0.2.50.2.52024-06-06
langchain vulnerable to path traversalCVE-2024-3571Medium< 0.0.3530.0.3532024-04-16
LangChain directory traversal vulnerabilityCVE-2024-28088Low< 0.0.3390.0.3392024-03-04
langchain Server-Side Request Forgery vulnerabilityCVE-2024-0243Low< 0.1.00.1.02024-02-26
Langchain Server-Side Request Forgery vulnerabilityCVE-2023-32786High< 0.0.3290.0.3292023-10-21
Langchain SQL Injection vulnerabilityCVE-2023-32785Critical< 0.0.2470.0.2472023-10-21
LangChain Server Side Request Forgery vulnerabilityCVE-2023-46229High>= 0, < 0.0.3170.0.3172023-10-19
Langchain vulnerable to arbitrary code execution via the evaluate function in the numexpr libraryCVE-2023-39631Critical< 0.0.3080.0.3082023-09-01
langchain vulnerable to arbitrary code executionCVE-2023-36281Critical< 0.0.3120.0.3122023-08-22
LangChain vulnerable to arbitrary code executionCVE-2023-38896Critical< 0.0.2360.0.2362023-08-15
LangChain vulnerable to arbitrary code executionCVE-2023-38860Critical>= 0, < 0.0.2470.0.2472023-08-15
LangChain vulnerable to arbitrary code executionCVE-2023-39659Critical< 0.0.3250.0.3252023-08-15
langchain Code Injection vulnerabilityCVE-2023-36095Critical< 0.0.2360.0.2362023-08-05
langchain vulnerable to arbitrary code executionCVE-2023-36188Critical< 0.0.2470.0.2472023-07-06
langchain SQL Injection vulnerabilityCVE-2023-36189High>= 0, < 0.0.2470.0.2472023-07-06
langchain arbitrary code execution vulnerabilityCVE-2023-36258Critical< 0.0.2470.0.2472023-07-03
Langchain vulnerable to arbitrary code executionCVE-2023-34541Critical< 0.0.2470.0.2472023-06-20
Langchain OS Command Injection vulnerabilityCVE-2023-34540Critical< 0.0.2250.0.2252023-06-14
LangChain vulnerable to code injectionCVE-2023-29374Critical<= 0.0.131No fix yet2023-04-05

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].