PyPI package
langchain
pkg:pypi/langchain
Vulnerabilities (20)
| CVE | Sev | CVSS | KEV | Affected versions | Fixed in | Published | Description |
|---|---|---|---|---|---|---|---|
| CVE-2026-45134 | hig | — | < 0.3.30 | 0.3.30 | May 13, 2026 | ## Description The LangSmith SDK's prompt pull methods (`pull_prompt` / `pull_prompt_commit` in Python, `pullPrompt` / `pullPromptCommit` in JS/TS) fetch and deserialize prompt manifests from the LangSmith Hub. These manifests may contain serialized LangChain objects and model c | |
| CVE-2024-8309 | — | < 0.2.0 | 0.2.0 | 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 m | ||
| CVE-2024-2965 | — | < 0.2.5 | 0.2.5 | Jun 6, 2024 | A Denial-of-Service (DoS) vulnerability exists in the `SitemapLoader` class of the `langchain-ai/langchain` repository, affecting all versions. The `parse_sitemap` method, responsible for parsing sitemaps and extracting URLs, lacks a mechanism to prevent infinite recursion when a | ||
| CVE-2024-3571 | — | < 0.0.353 | 0.0.353 | Apr 16, 2024 | langchain-ai/langchain is vulnerable to path traversal due to improper limitation of a pathname to a restricted directory ('Path Traversal') in its LocalFileStore functionality. An attacker can leverage this vulnerability to read or write files anywhere on the filesystem, potenti | ||
| CVE-2024-28088 | — | < 0.0.339 | 0.0.339 | Mar 3, 2024 | LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome | ||
| CVE-2024-0243 | — | < 0.1.0 | 0.1.0 | Feb 24, 2024 | With the following crawler configuration: ```python from bs4 import BeautifulSoup as Soup url = "https://example.com" loader = RecursiveUrlLoader( url=url, max_depth=2, extractor=lambda x: Soup(x, "html.parser").text ) docs = loader.load() ``` An attacker in control of the | ||
| CVE-2023-32786 | — | < 0.0.329 | 0.0.329 | Oct 20, 2023 | 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. | ||
| CVE-2023-46229 | — | < 0.0.317 | 0.0.317 | Oct 19, 2023 | LangChain before 0.0.317 allows SSRF via document_loaders/recursive_url_loader.py because crawling can proceed from an external server to an internal server. | ||
| CVE-2023-39631 | — | < 0.0.308 | 0.0.308 | 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 | — | < 0.0.312 | 0.0.312 | 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 | — | < 0.0.325 | 0.0.325 | 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 | — | < 0.0.236 | 0.0.236 | 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 | — | < 0.0.247 | 0.0.247 | Aug 15, 2023 | An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter. | ||
| CVE-2023-36095 | — | < 0.0.236 | 0.0.236 | Aug 5, 2023 | An issue in Harrison Chase langchain v.0.0.194 allows an attacker to execute arbitrary code via the python exec calls in the PALChain, affected functions include from_math_prompt and from_colored_object_prompt. | ||
| CVE-2023-36189 | — | < 0.0.247 | 0.0.247 | Jul 6, 2023 | SQL injection vulnerability in langchain before v0.0.247 allows a remote attacker to obtain sensitive information via the SQLDatabaseChain component. | ||
| CVE-2023-36188 | — | < 0.0.236 | 0.0.236 | Jul 6, 2023 | An issue in langchain v.0.0.64 allows a remote attacker to execute arbitrary code via the PALChain parameter in the Python exec method. | ||
| CVE-2023-36258 | — | < 0.0.247 | 0.0.247 | Jul 3, 2023 | An issue in LangChain before 0.0.236 allows an attacker to execute arbitrary code because Python code with os.system, exec, or eval can be used. | ||
| CVE-2023-34541 | — | < 0.0.247 | 0.0.247 | Jun 20, 2023 | Langchain 0.0.171 is vulnerable to Arbitrary code execution in load_prompt. | ||
| CVE-2023-34540 | — | < 0.0.225 | 0.0.225 | Jun 14, 2023 | Langchain before v0.0.225 was discovered to contain a remote code execution (RCE) vulnerability in the component JiraAPIWrapper (aka the JIRA API wrapper). This vulnerability allows attackers to execute arbitrary code via crafted input. As noted in the "releases/tag" reference, a | ||
| CVE-2023-29374 | — | <= 0.0.131 | — | 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. |
- affected < 0.3.30fixed 0.3.30
## Description The LangSmith SDK's prompt pull methods (`pull_prompt` / `pull_prompt_commit` in Python, `pullPrompt` / `pullPromptCommit` in JS/TS) fetch and deserialize prompt manifests from the LangSmith Hub. These manifests may contain serialized LangChain objects and model c
- CVE-2024-8309Oct 29, 2024affected < 0.2.0fixed 0.2.0
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 m
- CVE-2024-2965Jun 6, 2024affected < 0.2.5fixed 0.2.5
A Denial-of-Service (DoS) vulnerability exists in the `SitemapLoader` class of the `langchain-ai/langchain` repository, affecting all versions. The `parse_sitemap` method, responsible for parsing sitemaps and extracting URLs, lacks a mechanism to prevent infinite recursion when a
- CVE-2024-3571Apr 16, 2024affected < 0.0.353fixed 0.0.353
langchain-ai/langchain is vulnerable to path traversal due to improper limitation of a pathname to a restricted directory ('Path Traversal') in its LocalFileStore functionality. An attacker can leverage this vulnerability to read or write files anywhere on the filesystem, potenti
- CVE-2024-28088Mar 3, 2024affected < 0.0.339fixed 0.0.339
LangChain through 0.1.10 allows ../ directory traversal by an actor who is able to control the final part of the path parameter in a load_chain call. This bypasses the intended behavior of loading configurations only from the hwchase17/langchain-hub GitHub repository. The outcome
- CVE-2024-0243Feb 24, 2024affected < 0.1.0fixed 0.1.0
With the following crawler configuration: ```python from bs4 import BeautifulSoup as Soup url = "https://example.com" loader = RecursiveUrlLoader( url=url, max_depth=2, extractor=lambda x: Soup(x, "html.parser").text ) docs = loader.load() ``` An attacker in control of the
- CVE-2023-32786Oct 20, 2023affected < 0.0.329fixed 0.0.329
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.
- CVE-2023-46229Oct 19, 2023affected < 0.0.317fixed 0.0.317
LangChain before 0.0.317 allows SSRF via document_loaders/recursive_url_loader.py because crawling can proceed from an external server to an internal server.
- CVE-2023-39631Sep 1, 2023affected < 0.0.308fixed 0.0.308
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-2023-36281Aug 22, 2023affected < 0.0.312fixed 0.0.312
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-2023-39659Aug 15, 2023affected < 0.0.325fixed 0.0.325
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-2023-38896Aug 15, 2023affected < 0.0.236fixed 0.0.236
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-2023-38860Aug 15, 2023affected < 0.0.247fixed 0.0.247
An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter.
- CVE-2023-36095Aug 5, 2023affected < 0.0.236fixed 0.0.236
An issue in Harrison Chase langchain v.0.0.194 allows an attacker to execute arbitrary code via the python exec calls in the PALChain, affected functions include from_math_prompt and from_colored_object_prompt.
- CVE-2023-36189Jul 6, 2023affected < 0.0.247fixed 0.0.247
SQL injection vulnerability in langchain before v0.0.247 allows a remote attacker to obtain sensitive information via the SQLDatabaseChain component.
- CVE-2023-36188Jul 6, 2023affected < 0.0.236fixed 0.0.236
An issue in langchain v.0.0.64 allows a remote attacker to execute arbitrary code via the PALChain parameter in the Python exec method.
- CVE-2023-36258Jul 3, 2023affected < 0.0.247fixed 0.0.247
An issue in LangChain before 0.0.236 allows an attacker to execute arbitrary code because Python code with os.system, exec, or eval can be used.
- CVE-2023-34541Jun 20, 2023affected < 0.0.247fixed 0.0.247
Langchain 0.0.171 is vulnerable to Arbitrary code execution in load_prompt.
- CVE-2023-34540Jun 14, 2023affected < 0.0.225fixed 0.0.225
Langchain before v0.0.225 was discovered to contain a remote code execution (RCE) vulnerability in the component JiraAPIWrapper (aka the JIRA API wrapper). This vulnerability allows attackers to execute arbitrary code via crafted input. As noted in the "releases/tag" reference, a
- CVE-2023-29374Apr 5, 2023affected <= 0.0.131
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.