LLMMedium
CVE-2024-48141: A prompt injection vulnerability in the chatbox of Zhipu AI CodeGeeX v2.17.0 allows attackers to acc…
- Occurred
- Oct 24, 2024
- Published
- Oct 24, 2024
- Source
- NVD CVE
Summary
A prompt injection vulnerability in the chatbox of Zhipu AI CodeGeeX v2.17.0 allows attackers to access and exfiltrate all previous and subsequent chat data between the user and the AI assistant via a crafted message.
Tags
- CVE
- CVE-2024-48141
- cvss:HIGH
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: Prompt injection vulnerability in an AI chatbot allowing data exfiltration, classified as LLM security issue with medium severity due to data breach risk.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8