Informational scan, not a security audit. How this is computed.
API keys, passwords or tokens committed into the repo.
Nothing found by this check. ✓
Packages you depend on that have known security holes (CVEs).
CVE-2023-34540 Langchain OS Command Injection vulnerabilityCVE-2023-34541 Langchain vulnerable to arbitrary code executionCVE-2023-36095 langchain Code Injection vulnerabilityCVE-2023-36188 langchain vulnerable to arbitrary code executionCVE-2023-36258 langchain arbitrary code execution vulnerabilityCVE-2023-36281 langchain vulnerable to arbitrary code executionCVE-2023-38860 LangChain vulnerable to arbitrary code executionCVE-2023-38896 LangChain vulnerable to arbitrary code executionCVE-2023-39631 Langchain vulnerable to arbitrary code execution via the evaluate function in the numexpr libraryCVE-2023-39659 LangChain vulnerable to arbitrary code executionCVE-2023-32786 Langchain Server-Side Request Forgery vulnerabilityCVE-2023-36189 langchain SQL Injection vulnerabilityCVE-2023-46229 langchain: langchain SSRFCVE-2026-45134 LangSmith SDK: Public prompt pull deserializes untrusted manifests without trust boundary warningCVE-2024-2965 langchain-community: Langchain-community SitemapParser DoS VulnerabilityCVE-2024-3571 langchain vulnerable to path traversalCVE-2026-55443 LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loadersCVE-2024-0243 langchain Server-Side Request Forgery vulnerabilityCVE-2024-28088 LangChain directory traversal vulnerabilityCVE-2024-8309 langchain: SQL Injection in langchain-ai/langchainYour dependencies cross-checked against the OSV vulnerability database.
PYSEC-2023-109 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.PYSEC-2023-138 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_objePYSEC-2023-145 An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter.PYSEC-2023-146 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.PYSEC-2023-147 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.PYSEC-2023-151 An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via the via the a json file to the load_prompt parameter.PYSEC-2023-162 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.PYSEC-2023-18 In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.PYSEC-2023-91 Langchain 0.0.171 is vulnerable to Arbitrary Code Execution.PYSEC-2023-92 Langchain 0.0.171 is vulnerable to Arbitrary code execution in load_prompt.PYSEC-2023-98 An issue in langchain v.0.0.199 allows an attacker to execute arbitrary code via the PALChain in the python exec method.PYSEC-2026-372 Langchain SQL Injection vulnerabilityPYSEC-2022-42992 All versions of package gitpython are vulnerable to Remote Code Execution (RCE) due to improper user input validation, which makes it possible to inject a maliciously crafted remote URL into the clonePYSEC-2023-137 GitPython before 3.1.32 does not block insecure non-multi options in clone and clone_from. NOTE: this issue exists because of an incomplete fix for CVE-2022-24439.PYSEC-2026-2161 GitPython is a python library used to interact with Git repositories. Prior to version 3.1.47, _clone() validates multi_options as the original list, then executes shlex.split(" ".join(multi_options))PYSEC-2026-457 Arbitrary Code Execution in PillowPYSEC-2023-238 Deserialization of untrusted data in IPC and Parquet readers in PyArrow versions 0.14.0 to 14.0.0 allows arbitrary code execution. An application is vulnerable if it reads Arrow IPC, Feather or ParquePYSEC-2023-110 SQL injection vulnerability in langchain v.0.0.64 allows a remote attacker to obtain sensitive information via the SQLDatabaseChain component.PYSEC-2023-205 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.PYSEC-2024-118 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 sitePYSEC-2024-323 A vulnerability in the FAISS.deserialize_from_bytes function of langchain-ai/langchain allows for pickle deserialization of untrusted data. This can lead to the execution of arbitrary commands via thePYSEC-2026-1507 Langchain SQL Injection vulnerabilityPYSEC-2026-1508 Langchain Server-Side Request Forgery vulnerabilityPYSEC-2026-1510 langchain vulnerable to path traversalPYSEC-2026-2192 LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confCode that can be exploited: injection, hardcoded credentials and similar.
Nothing found by this check. ✓
Packages that look intentionally malicious: typosquats, sneaky install scripts.
This check didn’t finish — that’s not the same as “clean.” Try Check again above.
A signal about how the project is maintained — not a vulnerability in your code. It doesn’t affect the verdict above.
Maintenance & supply-chain hygiene. A signal about the project, not a vulnerability in your code.
This check didn’t finish — that’s not the same as “clean.” Try Check again above.