langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Unspecified product |
| No fix yet |
Original 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.
From the CVE record · mitre