Executive brief
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.
Affected products
- PyPI langchain
Junglewise Threat Intelligence
CVE-2023-29374: 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 met
CVE-2023-29374 · Severity: low · CVSS 3.1 · Published 2023-04-05
Technologies: langchain (PyPI). Vendors: PyPI.
Related threats
- PYSEC-2026-2561 - Denial of service in langchain-community
- PYSEC-2026-1507 - Langchain SQL Injection vulnerability
- PYSEC-2026-1514 - LangChain pickle deserialization of untrusted data
- PYSEC-2026-1510 - langchain vulnerable to path traversal
- PYSEC-2026-1509 - langchain Server-Side Request Forgery vulnerability