PT-2025-31216 · Unknown · Emailtoolkit+1

Jr61-Star · Published 2025-07-29 · Updated 2025-08-04 · CVE-2025-46059

Positive Technologies (AI Summary)

CVSS v3.1

9.8

Critical

Base vector

AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Name of the Vulnerable Software and Affected Versions langchain-ai version 0.3.51

Description langchain-ai version 0.3.51 contains 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. The supplier disputes the code-execution claim, stating the issue arises from user-written code that does not follow LangChain security practices.

Recommendations At the moment, there is no information about a newer version that contains a fix for this vulnerability.

Exploit

Code Injection

Weakness Enumeration

CWE-94

Related Identifiers

CVE-2025-46059

Affected Products

Emailtoolkit

Langchain-Ai

References · 13

• 🔥 https://github.com/Jr61-star/CVEs/blob/main/CVE-2025-46059.md · Exploit
• https://nvd.nist.gov/vuln/detail/CVE-2025-46059 · Security Note
• https://osv.dev/vulnerability/CVE-2025-46059 · Vendor Advisory
• https://github.com/langchain-ai/langchain/issues/30833 · Note
• https://github.com/langchain-ai/langchain-community/issues/217#issuecomment-3144824471 · Note
• https://t.me/CVEtracker/28671 · Telegram Post
• https://twitter.com/UjlakiMarci/status/1950225717620301867 · Twitter Post
• https://t.me/cveNotify/130722 · Telegram Post
• https://python.langchain.com/docs/security · Note
• https://twitter.com/CVEnew/status/1950208801296306244 · Twitter Post
• https://twitter.com/cracbot/status/1951961298666770706 · Twitter Post
• https://twitter.com/Andrewkek77/status/1950472050608320883 · Twitter Post
• https://twitter.com/VulmonFeeds/status/1950223459469934647 · Twitter Post