Langchain

19 CVEs product

Monthly

CVE-2026-25750 HIGH This Week

LangSmith Studio contains a URL parameter injection vulnerability that allows attackers to steal authentication tokens, user IDs, and workspace credentials from users who click malicious links, enabling account takeover and unauthorized access to workspace resources. Both LangSmith Cloud and self-hosted Kubernetes deployments are affected, with exploitation requiring social engineering to trick authenticated users into clicking attacker-controlled URLs. No patch is currently available for this high-severity vulnerability (CVSS 8.1).

Kubernetes Authentication Bypass Langsmith Langchain AI / ML
NVD GitHub VulDB
CVSS 3.1
8.1
EPSS
0.1%
CVE-2026-27966 CRITICAL POC PATCH Act Now

Code injection in Langflow CSV Agent node before 1.8.0. The node hardcodes allow_dangerous_code=True, enabling arbitrary code execution through crafted CSV files. EPSS 0.41% with PoC and patch available.

Python RCE Command Injection AI / ML Langflow +1
NVD GitHub
CVSS 3.1
9.8
EPSS
0.4%
CVE-2026-27795 MEDIUM PATCH This Month

LangChain's RecursiveUrlLoader in @langchain/community versions prior to 1.1.18 fails to validate redirect targets, allowing authenticated attackers to bypass SSRF protections by redirecting from whitelisted URLs to internal or metadata endpoints. An attacker with user credentials can exploit this to access sensitive internal resources or cloud metadata services through automatic redirect following. Affected applications should upgrade to version 1.1.18, which disables automatic redirects and re-validates each redirect destination.

SSRF AI / ML Langchain Redhat
NVD GitHub
CVSS 3.1
4.1
EPSS
0.0%
CVE-2026-27022 MEDIUM PATCH This Month

Query injection in @langchain/langgraph-checkpoint-redis allows authenticated users to manipulate RediSearch filter logic by injecting special syntax characters into user-provided keys and values, potentially bypassing access controls. An attacker with valid credentials could craft malicious filter parameters to alter query behavior and access unintended data. The vulnerability affects LangGraph checkpoint implementations using Redis storage and is fixed in version 1.0.2.

Redis AI / ML Langchain
NVD GitHub
CVSS 3.1
6.5
EPSS
0.0%
CVE-2026-26019 MEDIUM PATCH This Month

RecursiveUrlLoader in LangChain Community prior to 1.1.14 uses weak string-based URL validation that allows attackers to bypass the preventOutside crawling restriction by crafting domains with matching prefixes, potentially exposing the crawler to malicious or internal infrastructure endpoints. An attacker controlling a crawled webpage could inject links to cloud metadata services or private IP ranges, which the crawler would follow without validation, leading to information disclosure.

SSRF AI / ML Langchain Community Langchain Redhat
NVD GitHub
CVSS 3.1
4.1
EPSS
0.0%
CVE-2026-26013 LOW PATCH Monitor

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input. This vulnerability...

SSRF Langchain AI / ML
NVD GitHub VulDB
CVSS 3.1
3.7
EPSS
0.0%
CVE-2024-58340 HIGH POC This Week

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service (ReDoS) vulnerability in the MRKLOutputParser.parse() method (libs/langchain/langchain/agents/mrkl/output_parser.py). [CVSS 7.5 HIGH]

Denial Of Service AI / ML Langchain Redhat
NVD GitHub
CVSS 3.1
7.5
EPSS
0.1%
CVE-2025-65106 HIGH PATCH This Month

LangChain is a framework for building agents and LLM-powered applications. Rated high severity (CVSS 8.3), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

Code Injection Python Ssti Langchain AI / ML +1
NVD GitHub
CVSS 4.0
8.3
EPSS
0.1%
CVE-2025-58177 MEDIUM PATCH This Month

n8n is an open source workflow automation platform. Rated medium severity (CVSS 5.4), this vulnerability is remotely exploitable, low attack complexity. This Cross-Site Scripting (XSS) vulnerability could allow attackers to inject malicious scripts into web pages viewed by other users.

Information Disclosure XSS N8n Langchain AI / ML
NVD GitHub
CVSS 3.1
5.4
EPSS
0.0%
CVE-2025-9556 CRITICAL This Week

Langchaingo supports the use of jinja2 syntax when parsing prompts, which is in turn parsed using the gonja library v1.5.3. Rated critical severity (CVSS 9.8), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

Code Injection Langchain AI / ML
NVD GitHub
CVSS 3.1
9.8
EPSS
0.1%
CVE-2025-6984 HIGH PATCH This Month

The langchain-ai/langchain project, specifically the EverNoteLoader component, is vulnerable to XML External Entity (XXE) attacks due to insecure XML parsing. Rated high severity (CVSS 7.5), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

XXE Information Disclosure Langchain AI / ML Redhat
NVD
CVSS 3.0
7.5
EPSS
1.9%
CVE-2025-45150 CRITICAL Act Now

Insecure permissions in LangChain-ChatGLM-Webui commit ef829 allows attackers to arbitrarily view and download sensitive files via supplying a crafted request. Rated critical severity (CVSS 9.8), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

Information Disclosure Langchain Chatglm Webui Langchain AI / ML
NVD GitHub
CVSS 3.1
9.8
EPSS
0.1%
CVE-2025-6855 MEDIUM POC This Month

A vulnerability, which was classified as critical, has been found in chatchat-space Langchain-Chatchat up to 0.3.1. This issue affects some unknown processing of the file /v1/file. The manipulation of the argument flag leads to path traversal. The exploit has been disclosed to the public and may be used.

Path Traversal Langchain Chatchat Langchain AI / ML
NVD GitHub VulDB
CVSS 3.1
5.5
EPSS
0.2%
CVE-2025-6854 MEDIUM POC This Month

A vulnerability classified as problematic was found in chatchat-space Langchain-Chatchat up to 0.3.1. This vulnerability affects unknown code of the file /v1/files?purpose=assistants. The manipulation leads to path traversal. The attack can be initiated remotely. The exploit has been disclosed to the public and may be used.

Path Traversal Langchain Chatchat Langchain AI / ML
NVD GitHub VulDB
CVSS 3.1
4.3
EPSS
0.1%
CVE-2025-6853 MEDIUM POC This Month

A vulnerability classified as critical has been found in chatchat-space Langchain-Chatchat up to 0.3.1. This affects the function upload_temp_docs of the file /knowledge_base/upload_temp_docs of the component Backend. The manipulation of the argument flag leads to path traversal. It is possible to initiate the attack remotely. The exploit has been disclosed to the public and may be used.

Path Traversal Langchain Chatchat Langchain AI / ML
NVD GitHub VulDB
CVSS 3.1
6.3
EPSS
0.2%
CVE-2025-2828 CRITICAL POC PATCH Act Now

A remote code execution vulnerability in langchain-ai/langchain (CVSS 10.0). Risk factors: public PoC available. Vendor patch is available.

Microsoft SSRF Langchain Redhat AI / ML
NVD GitHub
CVSS 3.1
10.0
EPSS
0.1%
CVE-2024-12704 HIGH POC PATCH This Week

A vulnerability in the LangChainLLM class of the run-llama/llama_index repository, version v0.12.5, allows for a Denial of Service (DoS) attack. Rated high severity (CVSS 7.5), this vulnerability is remotely exploitable, no authentication required, low attack complexity. Public exploit code available.

Denial Of Service Llamaindex Langchain AI / ML Redhat
NVD GitHub
CVSS 3.0
7.5
EPSS
0.1%
CVE-2024-10940 MEDIUM PATCH This Month

A vulnerability in langchain-core versions >=0.1.17,<0.1.53, >=0.2.0,<0.2.43, and >=0.3.0,<0.3.15 allows unauthorized users to read arbitrary files from the host file system. Rated medium severity (CVSS 5.3), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

Information Disclosure Langchain AI / ML Redhat
NVD GitHub
CVSS 3.0
5.3
EPSS
0.1%
CVE-2025-21604 MEDIUM This Month

LangChain4j-AIDeepin is a Retrieval enhancement generation (RAG) project. Rated medium severity (CVSS 6.9), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

File Upload Langchain AI / ML
NVD GitHub
CVSS 4.0
6.9
EPSS
0.1%
CVE-2026-25750
EPSS 0% CVSS 8.1
HIGH This Week

LangSmith Studio contains a URL parameter injection vulnerability that allows attackers to steal authentication tokens, user IDs, and workspace credentials from users who click malicious links, enabling account takeover and unauthorized access to workspace resources. Both LangSmith Cloud and self-hosted Kubernetes deployments are affected, with exploitation requiring social engineering to trick authenticated users into clicking attacker-controlled URLs. No patch is currently available for this high-severity vulnerability (CVSS 8.1).

Kubernetes Authentication Bypass Langsmith +2
NVD GitHub VulDB
CVE-2026-27966
EPSS 0% CVSS 9.8
CRITICAL POC PATCH Act Now

Code injection in Langflow CSV Agent node before 1.8.0. The node hardcodes allow_dangerous_code=True, enabling arbitrary code execution through crafted CSV files. EPSS 0.41% with PoC and patch available.

Python RCE Command Injection +3
NVD GitHub
CVE-2026-27795
EPSS 0% CVSS 4.1
MEDIUM PATCH This Month

LangChain's RecursiveUrlLoader in @langchain/community versions prior to 1.1.18 fails to validate redirect targets, allowing authenticated attackers to bypass SSRF protections by redirecting from whitelisted URLs to internal or metadata endpoints. An attacker with user credentials can exploit this to access sensitive internal resources or cloud metadata services through automatic redirect following. Affected applications should upgrade to version 1.1.18, which disables automatic redirects and re-validates each redirect destination.

SSRF AI / ML Langchain +1
NVD GitHub
CVE-2026-27022
EPSS 0% CVSS 6.5
MEDIUM PATCH This Month

Query injection in @langchain/langgraph-checkpoint-redis allows authenticated users to manipulate RediSearch filter logic by injecting special syntax characters into user-provided keys and values, potentially bypassing access controls. An attacker with valid credentials could craft malicious filter parameters to alter query behavior and access unintended data. The vulnerability affects LangGraph checkpoint implementations using Redis storage and is fixed in version 1.0.2.

Redis AI / ML Langchain
NVD GitHub
CVE-2026-26019
EPSS 0% CVSS 4.1
MEDIUM PATCH This Month

RecursiveUrlLoader in LangChain Community prior to 1.1.14 uses weak string-based URL validation that allows attackers to bypass the preventOutside crawling restriction by crafting domains with matching prefixes, potentially exposing the crawler to malicious or internal infrastructure endpoints. An attacker controlling a crawled webpage could inject links to cloud metadata services or private IP ranges, which the crawler would follow without validation, leading to information disclosure.

SSRF AI / ML Langchain Community +2
NVD GitHub
CVE-2026-26013
EPSS 0% CVSS 3.7
LOW PATCH Monitor

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input. This vulnerability...

SSRF Langchain AI / ML
NVD GitHub VulDB
CVE-2024-58340
EPSS 0% CVSS 7.5
HIGH POC This Week

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service (ReDoS) vulnerability in the MRKLOutputParser.parse() method (libs/langchain/langchain/agents/mrkl/output_parser.py). [CVSS 7.5 HIGH]

Denial Of Service AI / ML Langchain +1
NVD GitHub
CVE-2025-65106
EPSS 0% CVSS 8.3
HIGH PATCH This Month

LangChain is a framework for building agents and LLM-powered applications. Rated high severity (CVSS 8.3), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

Code Injection Python Ssti +3
NVD GitHub
CVE-2025-58177
EPSS 0% CVSS 5.4
MEDIUM PATCH This Month

n8n is an open source workflow automation platform. Rated medium severity (CVSS 5.4), this vulnerability is remotely exploitable, low attack complexity. This Cross-Site Scripting (XSS) vulnerability could allow attackers to inject malicious scripts into web pages viewed by other users.

Information Disclosure XSS N8n +2
NVD GitHub
CVE-2025-9556
EPSS 0% CVSS 9.8
CRITICAL This Week

Langchaingo supports the use of jinja2 syntax when parsing prompts, which is in turn parsed using the gonja library v1.5.3. Rated critical severity (CVSS 9.8), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

Code Injection Langchain AI / ML
NVD GitHub
CVE-2025-6984
EPSS 2% CVSS 7.5
HIGH PATCH This Month

The langchain-ai/langchain project, specifically the EverNoteLoader component, is vulnerable to XML External Entity (XXE) attacks due to insecure XML parsing. Rated high severity (CVSS 7.5), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

XXE Information Disclosure Langchain +2
NVD
CVE-2025-45150
EPSS 0% CVSS 9.8
CRITICAL Act Now

Insecure permissions in LangChain-ChatGLM-Webui commit ef829 allows attackers to arbitrarily view and download sensitive files via supplying a crafted request. Rated critical severity (CVSS 9.8), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

Information Disclosure Langchain Chatglm Webui Langchain +1
NVD GitHub
CVE-2025-6855
EPSS 0% CVSS 5.5
MEDIUM POC This Month

A vulnerability, which was classified as critical, has been found in chatchat-space Langchain-Chatchat up to 0.3.1. This issue affects some unknown processing of the file /v1/file. The manipulation of the argument flag leads to path traversal. The exploit has been disclosed to the public and may be used.

Path Traversal Langchain Chatchat Langchain +1
NVD GitHub VulDB
CVE-2025-6854
EPSS 0% CVSS 4.3
MEDIUM POC This Month

A vulnerability classified as problematic was found in chatchat-space Langchain-Chatchat up to 0.3.1. This vulnerability affects unknown code of the file /v1/files?purpose=assistants. The manipulation leads to path traversal. The attack can be initiated remotely. The exploit has been disclosed to the public and may be used.

Path Traversal Langchain Chatchat Langchain +1
NVD GitHub VulDB
CVE-2025-6853
EPSS 0% CVSS 6.3
MEDIUM POC This Month

A vulnerability classified as critical has been found in chatchat-space Langchain-Chatchat up to 0.3.1. This affects the function upload_temp_docs of the file /knowledge_base/upload_temp_docs of the component Backend. The manipulation of the argument flag leads to path traversal. It is possible to initiate the attack remotely. The exploit has been disclosed to the public and may be used.

Path Traversal Langchain Chatchat Langchain +1
NVD GitHub VulDB
CVE-2025-2828
EPSS 0% CVSS 10.0
CRITICAL POC PATCH Act Now

A remote code execution vulnerability in langchain-ai/langchain (CVSS 10.0). Risk factors: public PoC available. Vendor patch is available.

Microsoft SSRF Langchain +2
NVD GitHub
CVE-2024-12704
EPSS 0% CVSS 7.5
HIGH POC PATCH This Week

A vulnerability in the LangChainLLM class of the run-llama/llama_index repository, version v0.12.5, allows for a Denial of Service (DoS) attack. Rated high severity (CVSS 7.5), this vulnerability is remotely exploitable, no authentication required, low attack complexity. Public exploit code available.

Denial Of Service Llamaindex Langchain +2
NVD GitHub
CVE-2024-10940
EPSS 0% CVSS 5.3
MEDIUM PATCH This Month

A vulnerability in langchain-core versions >=0.1.17,<0.1.53, >=0.2.0,<0.2.43, and >=0.3.0,<0.3.15 allows unauthorized users to read arbitrary files from the host file system. Rated medium severity (CVSS 5.3), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

Information Disclosure Langchain AI / ML +1
NVD GitHub
CVE-2025-21604
EPSS 0% CVSS 6.9
MEDIUM This Month

LangChain4j-AIDeepin is a Retrieval enhancement generation (RAG) project. Rated medium severity (CVSS 6.9), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

File Upload Langchain AI / ML
NVD GitHub

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy