Fluid Attacks Database

Description

LangChain vulnerable to code injection In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec() method.

Mitigation

Update Impact

Minimal update. May introduce new vulnerabilities or breaking changes.

Ecosystem	Component	Affected version	Patched versions
pypi	langchain	>=0 <=0.0.131	0.0.132

Aliases

1. CVE-2023-293742. NVD-2023-293743. OSV-2023-293744. GCVE-2023-29374

References

1. https://github.com/hwchase17/langchain/issues/10262. https://github.com/hwchase17/langchain/issues/8143. https://github.com/hwchase17/langchain/pull/11194. https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-18.yaml5. https://twitter.com/rharang/status/1641899743608463365/photo/1

Does your application use this vulnerable software?

During the free trial, our tools assess your application, identify vulnerabilities, and provide recommendations for their remediation.