CVE-2025-46059CRITICAL 9.8EPSS p47.2%

CVE-2025-46059CVE-2025-46059

Description

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.

Scoring

CVSS 3.19.8 (CRITICAL)
VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS0.67% probability of exploitation · percentile 47.2% · 2026-06-18T12:00:27Z
Published2025-07-29
Last modified2026-04-15

Underlying weaknesses· 1

CWE-94

References

  1. https://github.com/Jr61-star/CVEs/blob/main/CVE-2025-46059.md
  2. https://github.com/langchain-ai/langchain-community/issues/217#issuecomment-3144824471
  3. https://github.com/langchain-ai/langchain/issues/30833
  4. https://python.langchain.com/docs/security/

1

TypeTargetConfidenceTier
WeaknessImproper Control of Generation of Code ('Code Injection')cwe-940%live

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

CVE
CVE-2025-45150
CVE
CVE-2026-34070
CVE
CVE-2025-2828
CVE
CVE-2026-33654
CVE
CVE-2025-6855
CVE
CVE-2025-6853
Sourced from NVD + FIRST.org EPSS. Curated for EU compliance use cases by Adam Lundqvist, Founder at SQUR.