CVE-2025-46059

Summary

langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows attackers to execute arbitrary code and compromise the application via a crafted email message. NOTE: this is disputed by the Supplier because the code-execution issue was introduced by user-written code that does not adhere to the LangChain security practices.

Affected Software

VendorProductVersion RangeStatus
n/an/an/aaffected

Weaknesses

  • n/a

ADP Enrichment

CISA ADP Vulnrichment

  • SSVC:
  • Exploitation: poc
    • Automatable: yes
    • Technical Impact: total

References