UTC

langchain-core

9 published advisories; version 1.3.3 or later fixes all of them.

Registry
PyPI
Advisories
9
Latest fix
1.3.3
Exploited in the wild
None listed

Check your machine

Finds langchain-core 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-core@0.3.86
See the trace →
Provenance

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

0 of the last 10 releases of langchain-core 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.

  • 1.8.2
  • 1.8.1
  • 1.8.0
  • 1.7.7
  • 1.7.6
  • 1.7.5
  • 1.7.4
  • 1.7.3
  • 1.7.2
  • 1.7.1

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 vulnerable to unsafe deserialization of attacker-controlled objects through overly broad `load()` allowlistsCVE-2026-44843High<= 0.3.840.3.852026-05-08
LangChain vulnerable to unsafe deserialization of attacker-controlled objects through overly broad `load()` allowlistsCVE-2026-44843High>= 1.0.0, <= 1.3.21.3.32026-05-08
LangChain has incomplete f-string validation in prompt templatesCVE-2026-40087Medium< 0.3.830.3.842026-04-08
LangChain has incomplete f-string validation in prompt templatesCVE-2026-40087Medium>= 1.0.0a1, < 1.2.281.2.282026-04-08
LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functionsCVE-2026-34070High< 1.2.221.2.222026-03-27
LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messagesCVE-2026-26013Low< 1.2.111.2.112026-02-11
LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIsCVE-2025-68664Critical< 0.3.810.3.812025-12-23
LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIsCVE-2025-68664Critical>= 1.0.0, < 1.2.51.2.52025-12-23
LangChain Vulnerable to Template Injection via Attribute Access in Prompt TemplatesCVE-2025-65106High<= 0.3.790.3.802025-11-20
LangChain Vulnerable to Template Injection via Attribute Access in Prompt TemplatesCVE-2025-65106High>= 1.0.0, <= 1.0.61.0.72025-11-20
langchain-core allows unauthorized users to read arbitrary files from the host file systemCVE-2024-10940Medium>= 0.1.17, < 0.1.530.1.532025-03-20
langchain-core allows unauthorized users to read arbitrary files from the host file systemCVE-2024-10940Medium>= 0.2.0, < 0.2.430.2.432025-03-20
langchain-core allows unauthorized users to read arbitrary files from the host file systemCVE-2024-10940Medium>= 0.3.0, < 0.3.150.3.152025-03-20
LangChain's XMLOutputParser vulnerable to XML Entity ExpansionCVE-2024-1455Medium< 0.1.350.1.352024-03-26
LangChain directory traversal vulnerabilityCVE-2024-28088Low>= 0, < 0.1.300.1.302024-03-04

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].