CyberRota Analysis
AI-GeneratedThe vulnerability allows attackers to exploit the Custom AI Instructions feature in Context7 versions up to 2.1.2, enabling them to inject unsanitized content that can lead to the execution of malicious commands in connected AI coding agents. This could result in credential exfiltration from environment files and destructive file deletion on the victim's machine during routine operations. Organizations utilizing Context7 should prioritize patching this vulnerability to protect against potential data breaches and system compromise.
Original NVD Description
Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instructions to exfiltrate credentials from environment files to an attacker-controlled service and perform destructive file deletion on the victim's machine when the agent makes a routine library documentation request.