Langchain

Vendor:

First CVE: Apr 5, 2023 · Active for 3 years

28
Total CVEs
More Total CVEs than 96% of tracked products
7.0
Avg CVEs / Year
Higher CVE frequency than 92% of tracked products
8.7
Avg CVSS
Higher Avg CVSS than 78% of tracked products
0.0%
KEV Rate
Bottom 1%

Trends Over Time

The number and severity of CVEs published that impact Langchain over time

Volume of CVEsAvg CVSS Base Score
First CVE
Apr 5, 2023
3 years ago
Most Recent CVE
Jun 22, 2026
34 days ago

CVE Severity & Scoring

Langchain28 CVEs
All CVEs352,713 CVEs
MediumHighCritical
Attack Vector
Local3 (10.7%)
Network25 (89.3%)
Unknown0 (0.0%)
Physical0 (0.0%)
Adjacent Network0 (0.0%)
Attack Complexity
Low25 (89.3%)
High3 (10.7%)
Unknown0 (0.0%)
User Interaction
None26 (92.9%)
Unknown0 (0.0%)
Required2 (7.1%)
Privileges Required
Low5 (17.9%)
High0 (0.0%)
None23 (82.1%)
Unknown0 (0.0%)

Top CVEs

Signals from CVEs in this product scope (28 CVEs).

28 CVEs · Highest risk first

CVEPublishedCVSSRiskKEVExploit
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.
Apr 5, 20239.853NONO
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.
Oct 19, 20238.852NONO
LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run o
May 26, 20268.236NONO
A Server-Side Request Forgery (SSRF) vulnerability exists in the RequestsToolkit component of the langchain-community package (specifically, langchain_community.agent_toolkits.open
Jun 23, 202510.035NONO
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 unauthoriz
Oct 29, 20249.835NONO
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.
Aug 15, 20239.830NONO
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.
Aug 15, 20239.830NONO
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.
Jul 3, 20239.830NONO
Langchain 0.0.171 is vulnerable to Arbitrary code execution in load_prompt.
Jun 20, 20239.830NONO
An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter.
Aug 15, 20239.829NONO

Exploit Exposure

Signals from CVEs in this product scope (28 CVEs).

CISA KEV
0 CVEs
0.0% of CVEs· Bottom 1%
Metasploit
0 CVEs
0.0% of CVEs· Bottom 1%
Nuclei
0 CVEs
0.0% of CVEs· Bottom 1%
ExploitDB
0 CVEs
0.0% of CVEs· Bottom 1%

Social Chatter

Signals from CVEs in this product scope (28 CVEs).

Media Mentions

Signals from CVEs in this product scope (28 CVEs).

Top CNAs Publishing CVEs For Langchain

Top CWEs

Versions

VersionCVE CountAvg CVSSAvg EPSSKEVExploits
0.2.519.813.8%00
0.0.6428.71.6%00
0.0.35118.81.9%00
0.0.2619.80.6%00
0.0.24519.81.3%00
0.0.23119.81.2%00
0.0.19919.81.1%00
0.0.19419.81.1%00
0.0.17139.81.8%00