Critical severity9.8NVD Advisory· Published Aug 22, 2023· Updated Jun 17, 2026
CVE-2023-36281
CVE-2023-36281
Description
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
langchainPyPI | < 0.0.312 | 0.0.312 |
Affected products
3(expand)+ 1 more
- (no CPE)
- cpe:2.3:a:langchain:langchain:0.0.171:*:*:*:*:*:*:*
Patches
Vulnerability mechanics
References
8- aisec.today/LangChain-2e6244a313dd46139c5ef28cbcab9e55nvdExploitThird Party AdvisoryWEB
- github.com/hwchase17/langchain/issues/4394nvdExploitIssue TrackingVendor AdvisoryWEB
- github.com/advisories/GHSA-7gfq-f96f-g85jghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2023-36281ghsaADVISORY
- github.com/langchain-ai/langchain/commit/22abeb9f6cc555591bf8e92b5e328e43aa07ff6cghsaWEB
- github.com/langchain-ai/langchain/pull/10252ghsaWEB
- github.com/langchain-ai/langchain/releases/tag/v0.0.312nvdWEB
- github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-151.yamlghsaWEB
News mentions
0No linked articles in our index yet.