# langchain (PyPI) vulnerabilities 22 known vulnerabilities (3 critical, 3 high, 5 medium, 1 low), with the versions each affects and the releases that fix them. ## At a glance - Latest release: not known (cve.now hasn't read this package's releases) - Newest unaffected release: not known without release data - Weekly downloads: 37.1M - Dependents: 3,166 - Registry: https://pypi.org/project/langchain/ ## Advisories (22) ### [CVE-2026-55443](https://cve.now/CVE-2026-55443): LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders - Severity: Medium 5.1 - Published: Jun 22, 2026 - Affected: fixed in 1.3.9. ### [CVE-2026-45134](https://cve.now/CVE-2026-45134): LangSmith Client SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning - Severity: High 7.1 - Published: May 27, 2026 - Affected: fixed in 0.3.30. ### [CVE-2024-8309](https://cve.now/CVE-2024-8309): SQL Injection in langchain-ai/langchain - Severity: Medium 4.9 - Published: Oct 29, 2024 - Affected: fixed in 0.2.0. ### [CVE-2024-5998](https://cve.now/CVE-2024-5998): Deserialization of Untrusted Data in langchain-ai/langchain - Severity: Medium 5.2 - Published: Sep 17, 2024 - Affected: fixed in 0.2.9. ### [CVE-2024-2965](https://cve.now/CVE-2024-2965): Denial-of-Service in LangChain SitemapLoader in langchain-ai/langchain - Severity: Medium 4.2 - Published: Jun 6, 2024 - Affected: fixed in 0.2.5; fixed in 0.2.5. ### [CVE-2024-3571](https://cve.now/CVE-2024-3571): Path Traversal in langchain-ai/langchain - Severity: Medium 6.5 - Published: Apr 16, 2024 - Affected: fixed in 0.0.353. ### [CVE-2024-28088](https://cve.now/CVE-2024-28088): 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… - Severity: High 8.1 - Published: Mar 3, 2024 - Affected: fixed in 0.0.339; fixed in 0.1.11. ### [CVE-2024-0243](https://cve.now/CVE-2024-0243): Server-side Request Forgery In Recursive URL Loader - Severity: Low 3.7 - Published: Feb 24, 2024 - Affected: fixed in 0.1.0. ### [CVE-2023-32786](https://cve.now/CVE-2023-32786): In Langchain through 0.0.155, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially… - Severity: Unrated - Published: Oct 20, 2023 - Affected: fixed in 0.0.329. ### [CVE-2023-46229](https://cve.now/CVE-2023-46229): LangChain before 0.0.317 allows SSRF via document\_loaders/recursive\_url\_loader.py because crawling can proceed from an external server to… - Severity: Unrated - Published: Oct 19, 2023 - Affected: fixed in 0.0.317; fixed in 0.0.317. ### [CVE-2023-39631](https://cve.now/CVE-2023-39631): 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… - Severity: Unrated - Published: Sep 1, 2023 - Affected: fixed in 0.0.308; fixed in 0.0.308. ### [CVE-2023-36281](https://cve.now/CVE-2023-36281): An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a JSON file to load\_prompt. - Severity: Critical 9.8 - Published: Aug 22, 2023 - Affected: fixed in 0.0.171; fixed in 0.0.312. ### [CVE-2023-39659](https://cve.now/CVE-2023-39659): 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… - Severity: Unrated - Published: Aug 15, 2023 - Affected: fixed in 0.0.233; fixed in 0.0.325. ### [CVE-2023-38896](https://cve.now/CVE-2023-38896): 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… - Severity: Unrated - Published: Aug 15, 2023 - Affected: fixed in 0.0.195; fixed in 0.0.236. ### [CVE-2023-38860](https://cve.now/CVE-2023-38860): An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter. - Severity: Unrated - Published: Aug 15, 2023 - Affected: fixed in 0.0.247. ### [CVE-2023-36095](https://cve.now/CVE-2023-36095): 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… - Severity: Unrated - Published: Aug 5, 2023 - Affected: fixed in 0.0.236. ### [CVE-2023-36189](https://cve.now/CVE-2023-36189): SQL injection vulnerability in langchain before v0.0.247 allows a remote attacker to obtain sensitive information via the SQLDatabaseChain… - Severity: High 7.5 - Published: Jul 6, 2023 - Affected: fixed in 0.0.247. ### [CVE-2023-36188](https://cve.now/CVE-2023-36188): 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. - Severity: Unrated - Published: Jul 6, 2023 - Affected: fixed in 0.0.247. ### [CVE-2023-36258](https://cve.now/CVE-2023-36258): 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… - Severity: Unrated - Published: Jul 3, 2023 - Affected: fixed in 0.0.247. ### [CVE-2023-34541](https://cve.now/CVE-2023-34541): Langchain 0.0.171 is vulnerable to Arbitrary code execution in load\_prompt. - Severity: Critical 9.8 - Published: Jun 20, 2023 - Affected: fixed in 0.0.247. ### [CVE-2023-34540](https://cve.now/CVE-2023-34540): Langchain before v0.0.225 was discovered to contain a remote code execution (RCE) vulnerability in the component JiraAPIWrapper (aka the… - Severity: Unrated - Published: Jun 14, 2023 - Affected: fixed in 0.0.225. ### [CVE-2023-29374](https://cve.now/CVE-2023-29374): In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec… - Severity: Critical 9.8 - Published: Apr 5, 2023 - Affected: through 0.0.131; fixed in 0.0.132. --- Source: cve.now Built by [Sazabi](https://www.sazabi.com/?utm_source=cve-now&utm_medium=markdown), AI-native observability and security: automatic issue detection, plain-language log search and live dashboards. Page: https://cve.now/packages/pypi/langchain Site guide for agents: https://cve.now/llms.txt Uses NVD data; not endorsed by NVD.