| Component | LangChain |
| Severity | high (CVSS 7.5) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N |
| Published (NVD) | 2023-10-20 |
| Last modified | 2026-06-17 |
| Affected versions | langchain <= 0.0.155 |
| Fixed in | see the vendor advisory |
| Weakness | CWE-74 |
| CISA KEV | not listed |
NVD description
In Langchain through 0.0.155, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks.
What to do
- NVD lists no fixed version yet: follow the vendor advisory below and keep LangChain off the public internet until a fix ships.
- Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
Other LangChain CVEs
LangChain is a framework for building LLM-powered applications. Prior to 1.1.1, @langchain/redis does not escape attacker-controlled values...
LangChain is a framework for building LLM-powered applications. Prior to 1.3.1, MongoDBChatMessageHistory does not enforce the documented st...
The OpenAI-compatible file upload endpoint `/v1/files` in Langchain-Chatchat 0.3.0 is vulnerable to path traversal. An attacker can write fi...
The /knowledge_base/upload_temp_docs temporary document upload endpoint in Langchain Chatchat 0.3.1 is vulnerable to path traversal. By craf...
The knowledge base creation and document upload interfaces in Langchain-Chatchat 0.3.0;0.3.1 is vulnerable to path traversal. An attacker ca...
LangChain MongoDB provides integrations between MongoDB, Atlas, LangChain, and LangGraph. Prior to langgraph-checkpoint-mongodb 0.3.0 and la...