- Latest release
- Not known: cve.now hasn't read this package's releases
- Newest unaffected release
- Not known without release data
- Advisories
- 22 · 3 critical, 3 high, 5 medium, 1 low
- Weekly downloads
- 37.1M
- Dependents
- 3,166
- Registry
- PyPI
Advisories 22
- CVE-2026-55443Medium 5.1
LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders
Affected: fixed in 1.3.9.
- CVE-2026-45134High 7.1
LangSmith Client SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning
Affected: fixed in 0.3.30.
- CVE-2024-8309Medium 4.9
SQL Injection in langchain-ai/langchain
Affected: fixed in 0.2.0.
- CVE-2024-5998Medium 5.2
Deserialization of Untrusted Data in langchain-ai/langchain
Affected: fixed in 0.2.9.
- CVE-2024-2965Medium 4.2
Denial-of-Service in LangChain SitemapLoader in langchain-ai/langchain
Affected: fixed in 0.2.5; fixed in 0.2.5.
- CVE-2024-3571Medium 6.5
Path Traversal in langchain-ai/langchain
Affected: fixed in 0.0.353.
- CVE-2024-28088High 8.1
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…
Affected: fixed in 0.0.339; fixed in 0.1.11.
- CVE-2024-0243Low 3.7
Server-side Request Forgery In Recursive URL Loader
Affected: fixed in 0.1.0.
- CVE-2023-32786Unrated
In Langchain through 0.0.155, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially…
Affected: fixed in 0.0.329.
- CVE-2023-46229Unrated
LangChain before 0.0.317 allows SSRF via document_loaders/recursive_url_loader.py because crawling can proceed from an external server to…
Affected: fixed in 0.0.317; fixed in 0.0.317.
- CVE-2023-39631Unrated
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…
Affected: fixed in 0.0.308; fixed in 0.0.308.
- CVE-2023-36281Critical 9.8
An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a JSON file to load_prompt.
Affected: fixed in 0.0.171; fixed in 0.0.312.
- CVE-2023-39659Unrated
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…
Affected: fixed in 0.0.233; fixed in 0.0.325.
- CVE-2023-38896Unrated
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…
Affected: fixed in 0.0.195; fixed in 0.0.236.
- CVE-2023-38860Unrated
An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter.
Affected: fixed in 0.0.247.
Show all 22 advisoriesShow fewer advisories
- CVE-2023-36095Unrated
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: fixed in 0.0.236.
- CVE-2023-36189High 7.5
SQL injection vulnerability in langchain before v0.0.247 allows a remote attacker to obtain sensitive information via the SQLDatabaseChain…
Affected: fixed in 0.0.247.
- CVE-2023-36188Unrated
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.
Affected: fixed in 0.0.247.
- CVE-2023-36258Unrated
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…
Affected: fixed in 0.0.247.
- CVE-2023-34541Critical 9.8
Langchain 0.0.171 is vulnerable to Arbitrary code execution in load_prompt.
Affected: fixed in 0.0.247.
- CVE-2023-34540Unrated
Langchain before v0.0.225 was discovered to contain a remote code execution (RCE) vulnerability in the component JiraAPIWrapper (aka the…
Affected: fixed in 0.0.225.
- CVE-2023-29374Critical 9.8
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec…
Affected: through 0.0.131; fixed in 0.0.132.