This site currently shows sample data for demonstration.

Vulnerabilities

CVE-2023-29374 | BDVDB-2026-199351 Detail

Description#

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

Impact#

Per CVSS v3.1: confidentiality impact high, integrity impact high, availability impact high. Attack vector: network.

Weaknesses#

  • CWE-74 Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

References#

Exploit#

No public exploit known

History#

  1. Version 1Record published in the CVE List.
  2. Version 2Most recent update recorded in the CVE List.