CVE-2026-75130
CriticalCVSS 9.0Summary
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 exfiltrate credentials from environment files and perform destructive file deletion on the victim's machine.
Risk Assessment
The attack can lead to credential theft and destructive file deletion, compromising data confidentiality and integrity and causing operational disruptions.
Recommendation
Update Context7 to a version above 2.1.2 if available, and limit trust in external content in AI agent configurations.
Original NVD description (English source)
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.