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 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.
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.
```Code``` unterstützt. Zero-Day & Vulnerability Intelligence Hub
Echtzeit-Tracking mit EPSS Exploit-Wahrscheinlichkeiten, Angriffsvektor-Decodern und KI-Patch-Anleitungen.
📊 Historien-Charts — Criticals-Trend · Vendors · EPSS-Verteilung
| Tier | CVEs | Anteil |
|---|---|---|
| ≥90 % | 720 | 0,2 % |
| ≥50 % | 3.223 | 0,9 % |
| ≥10 % | 22.114 | 6,0 % |
| <10 % | 341.998 | 92,9 % |
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 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.
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 messag
Noch keine Analyse zu CVE-2025-46059
Sei der Erste: Einschätzung, Betroffenheit, Workaround oder PoC — mit Antworten im Thread.