CVE-2025-46059
langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the...
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Exploit likelihood
What each source reports
CVE List Score used
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.
- Record
CVE-2025-46059- CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-94
- Updated
- 2026-11-02
EUVDEUVD-2025-23002
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.
- Record
EUVD-2025-23002- CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-3g6x-vq45-v2jv
langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the...
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.
- Record
GHSA-3g6x-vq45-v2jv- CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-94
- Updated
- 2026-11-02
NVD
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.
- Record
CVE-2025-46059- CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-94
- Updated
- 2026-11-02
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2025-46059 is a critical vulnerability (CVSS 9.8), published July 29, 2025. Its validity is disputed. EPSS puts the chance of exploitation in the next 30 days at 0.84%, the 58th percentile.