LLMHigh
CVE-2025-46059: langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the Gma…
- Occurred
- Jul 29, 2025
- Published
- Jul 29, 2025
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2025-46059
- cvss:CRITICAL
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: LangChain is an LLM framework with a critical prompt injection vulnerability enabling arbitrary code execution.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8