CVE-2024-48142: A prompt injection vulnerability in the chatbox of Butterfly Effect Limited Monica ChatGPT AI Assistant v2.4.0 allows at
highvulnerabilityLLM-Specific
security
Summary
CVE-2024-48142 is a prompt injection vulnerability (a technique where attackers hide malicious instructions in text sent to an AI) in Monica ChatGPT AI Assistant v2.4.0 that lets attackers steal all chat messages between a user and the AI through a specially crafted message.
Vulnerability Details
CVSS Score
7.5(high)
EPSS (30-day exploit probability)
EPSS: 0.1%
Classification
Attack Type
Prompt InjectionData Extraction
Attack SophisticationModerate
Impact (CIA+S)
confidentiality
Affected Vendors
Related Issues
criticalhigh
CVE-2025-45150: Insecure permissions in LangChain-ChatGLM-Webui commit ef829 allows attackers to arbitrarily view and download sensitive
Similar attackNVD/CVE Database
CVE-2025-54868: LibreChat is a ChatGPT clone with additional features. In versions 0.0.6 through 0.7.7-rc1, an exposed testing endpoint
Similar attack
Original source: https://nvd.nist.gov/vuln/detail/CVE-2024-48142
First tracked: February 15, 2026 at 08:50 PM
Classified by LLM (prompt v3) · confidence: 85%