- 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.
- Source
- cve@mitre.org
- NVD status
- Deferred
- CNA Tags
- disputed
CVSS 3.1
- Type
- Secondary
- Base score
- 9.8
- Impact score
- 5.9
- Exploitability score
- 3.9
- Vector string
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- Severity
- CRITICAL
- 134c704f-9b21-4f2e-91b3-4a467353bcc0
- CWE-94
- Hype score
- Not currently trending
CVE-2025-46059 (CVSS:9.8, CRITICAL) is Awaiting Analysis. langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component...https://t.co/rTCP0gGKOS #cybersecurityawareness #cybersecurity #CVE #infosec #hacker #nvd #mitre
@cracbot
3 Aug 2025
9 Impressions
0 Retweets
0 Likes
0 Bookmarks
0 Replies
0 Quotes
wanna hack and take control of an AI agent with a crafted email? 🟥 CVE-2025-46059, CVSS: 9.8 (#Critical) langchain-ai version 0.3.51 An indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows attackers to execute arbitrary code via
@UjlakiMarci
29 Jul 2025
573 Impressions
2 Retweets
3 Likes
1 Bookmark
1 Reply
1 Quote
CVE-2025-46059 Indirect Prompt Injection in Langchain AI GmailToolkit Enables Arbitrary Code Execution https://t.co/uRNjbYMdCg
@VulmonFeeds
29 Jul 2025
18 Impressions
0 Retweets
0 Likes
0 Bookmarks
0 Replies
0 Quotes
CVE-2025-46059 langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows attackers to execut… https://t.co/0cq1Xejlyz
@CVEnew
29 Jul 2025
360 Impressions
0 Retweets
1 Like
0 Bookmarks
0 Replies
0 Quotes