Langchain AI
Products
22Recent CVEs
89| CVE | Vendor / Product | Sev | Risk | CVSS | EPSS | KEV | Published | Description |
|---|---|---|---|---|---|---|---|---|
| CVE-2025-46059 | Cri | 0.64 | 9.8 | 0.01 | Jul 29, 2025 | langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows attackers to execute arbitrary code and compromise the application via a crafted email message. NOTE: this is disputed by the… | ||
| CVE-2025-68664 | Cri | 0.60 | 9.3 | 0.43 | Dec 23, 2025 | LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing… | ||
| CVE-2025-2828 | Cri | 0.60 | 10.0 | 0.21 | Jun 23, 2025 | A Server-Side Request Forgery (SSRF) vulnerability exists in the RequestsToolkit component of the langchain-community package (specifically, langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit) in langchain-ai/langchain version 0.0.27. This vulnerability occurs… | ||
| CVE-2023-29374 | Cri | 0.60 | 9.8 | 0.40 | Apr 5, 2023 | In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method. | ||
| CVE-2026-51882 | Cri | 0.59 | 9.1 | 0.01 | Oct 1, 2026 | The OpenAI-compatible file upload endpoint `/v1/files` in Langchain-Chatchat 0.3.0 is vulnerable to path traversal. An attacker can write files to arbitrary locations outside the `openai_files` directory by crafting malicious filenames. | ||
| CVE-2026-54769 | Cri | 0.58 | 10.0 | 0.01 | Jul 10, 2026 | Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its `TableChatAgent` and `VectorStore` capabilities. When these agents evaluate… | ||
| CVE-2024-8309 | Cri | 0.58 | 9.8 | 0.14 | Oct 29, 2024 | A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data manipulation, data exfiltration, denial of service (DoS) by deleting all data, breaches in… | ||
| CVE-2026-51884 | Cri | 0.57 | 9.8 | 0.01 | Oct 1, 2026 | The /knowledge_base/upload_temp_docs temporary document upload endpoint in Langchain Chatchat 0.3.1 is vulnerable to path traversal. By crafting malicious filenames, an attacker can write files to arbitrary locations on the server, bypassing the intended restrictions on the… | ||
| CVE-2026-25879 | Cri | 0.57 | 9.8 | 0.01 | Jun 1, 2026 | Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or… | ||
| CVE-2025-46725 | Cri | 0.57 | 9.8 | 0.01 | May 20, 2025 | Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `LanceDocChatAgent` uses pandas eval() through `compute_from_docs()`. As a result, an attacker may be able to make the agent run malicious commands through… | ||
| CVE-2025-46724 | Cri | 0.57 | 9.8 | 0.01 | May 20, 2025 | Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `TableChatAgent` uses `pandas eval()`. If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection.… | ||
| CVE-2024-7042 | Cri | 0.57 | 9.8 | 0.00 | Oct 29, 2024 | A vulnerability in the GraphCypherQAChain class of langchain-ai/langchainjs versions 0.2.5 and all versions with this class allows for prompt injection, leading to SQL injection. This vulnerability permits unauthorized data manipulation, data exfiltration, denial of service… | ||
| CVE-2024-46946 | Cri | 0.57 | 9.8 | 0.01 | Sep 19, 2024 | langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6… | ||
| CVE-2024-27444 | Cri | 0.57 | 9.8 | 0.01 | Feb 26, 2024 | langchain_experimental (aka LangChain Experimental) in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the __import__, __subclasses__, __builtins__, __globals__, __getattribute__, __bases__, __mro__, or __base__ attribute… | ||
| CVE-2023-44467 | Cri | 0.57 | 9.8 | 0.01 | Oct 9, 2023 | langchain_experimental (aka LangChain Experimental) in LangChain before 0.0.306 allows an attacker to bypass the CVE-2023-36258 fix and execute arbitrary code via __import__ in Python code, which is not prohibited by pal_chain/base.py. | ||
| CVE-2023-39631 | Cri | 0.57 | 9.8 | 0.02 | Sep 1, 2023 | An issue in LanChain-ai Langchain v.0.0.245 allows a remote attacker to execute arbitrary code via the evaluate function in the numexpr library. | ||
| CVE-2023-36281 | Cri | 0.57 | 9.8 | 0.03 | Aug 22, 2023 | An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a JSON file to load_prompt. This is related to __subclasses__ or a template. | ||
| CVE-2023-39659 | Cri | 0.57 | 9.8 | 0.02 | Aug 15, 2023 | An issue in langchain langchain-ai v.0.0.232 and before allows a remote attacker to execute arbitrary code via a crafted script to the PythonAstREPLTool._run component. | ||
| CVE-2023-38896 | Cri | 0.57 | 9.8 | 0.02 | Aug 15, 2023 | An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to execute arbitrary code via the from_math_prompt and from_colored_object_prompt functions. | ||
| CVE-2023-38860 | Cri | 0.57 | 9.8 | 0.01 | Aug 15, 2023 | An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter. |
- risk 0.64cvss 9.8epss 0.01
langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows attackers to execute arbitrary code and compromise the application via a crafted email message. NOTE: this is disputed by the…
- risk 0.60cvss 9.3epss 0.43
LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing…
- risk 0.60cvss 10.0epss 0.21
A Server-Side Request Forgery (SSRF) vulnerability exists in the RequestsToolkit component of the langchain-community package (specifically, langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit) in langchain-ai/langchain version 0.0.27. This vulnerability occurs…
- risk 0.60cvss 9.8epss 0.40
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.
- risk 0.59cvss 9.1epss 0.01
The OpenAI-compatible file upload endpoint `/v1/files` in Langchain-Chatchat 0.3.0 is vulnerable to path traversal. An attacker can write files to arbitrary locations outside the `openai_files` directory by crafting malicious filenames.
- risk 0.58cvss 10.0epss 0.01
Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its `TableChatAgent` and `VectorStore` capabilities. When these agents evaluate…
- risk 0.58cvss 9.8epss 0.14
A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data manipulation, data exfiltration, denial of service (DoS) by deleting all data, breaches in…
- risk 0.57cvss 9.8epss 0.01
The /knowledge_base/upload_temp_docs temporary document upload endpoint in Langchain Chatchat 0.3.1 is vulnerable to path traversal. By crafting malicious filenames, an attacker can write files to arbitrary locations on the server, bypassing the intended restrictions on the…
- risk 0.57cvss 9.8epss 0.01
Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or…
- risk 0.57cvss 9.8epss 0.01
Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `LanceDocChatAgent` uses pandas eval() through `compute_from_docs()`. As a result, an attacker may be able to make the agent run malicious commands through…
- risk 0.57cvss 9.8epss 0.01
Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `TableChatAgent` uses `pandas eval()`. If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection.…
- risk 0.57cvss 9.8epss 0.00
A vulnerability in the GraphCypherQAChain class of langchain-ai/langchainjs versions 0.2.5 and all versions with this class allows for prompt injection, leading to SQL injection. This vulnerability permits unauthorized data manipulation, data exfiltration, denial of service…
- risk 0.57cvss 9.8epss 0.01
langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6…
- risk 0.57cvss 9.8epss 0.01
langchain_experimental (aka LangChain Experimental) in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the __import__, __subclasses__, __builtins__, __globals__, __getattribute__, __bases__, __mro__, or __base__ attribute…
- risk 0.57cvss 9.8epss 0.01
langchain_experimental (aka LangChain Experimental) in LangChain before 0.0.306 allows an attacker to bypass the CVE-2023-36258 fix and execute arbitrary code via __import__ in Python code, which is not prohibited by pal_chain/base.py.
- risk 0.57cvss 9.8epss 0.02
An issue in LanChain-ai Langchain v.0.0.245 allows a remote attacker to execute arbitrary code via the evaluate function in the numexpr library.
- risk 0.57cvss 9.8epss 0.03
An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a JSON file to load_prompt. This is related to __subclasses__ or a template.
- risk 0.57cvss 9.8epss 0.02
An issue in langchain langchain-ai v.0.0.232 and before allows a remote attacker to execute arbitrary code via a crafted script to the PythonAstREPLTool._run component.
- risk 0.57cvss 9.8epss 0.02
An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to execute arbitrary code via the from_math_prompt and from_colored_object_prompt functions.
- risk 0.57cvss 9.8epss 0.01
An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter.