CVE-2026-75130: Context7 2.1.2 Prompt Injection via Custom AI Instructions
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.
Affected Software
Event History
Frequently Asked Questions
Who is realistically exposed to this issue?
Users of connected AI coding agents that make routine library documentation requests through the Context7 MCP server are exposed. The issue can lead to credential exfiltration from environment files and destructive file deletion on the machine where the agent operates.
What does an attacker need to exploit it?
An attacker needs the ability to poison content provided through the Custom AI Instructions feature. Exploitation occurs when a connected AI coding agent processes that unsanitized content during a routine library documentation request.
What could exploitation allow an attacker to do?
The described malicious instructions can direct the agent to exfiltrate credentials from environment files to an attacker-controlled service and delete files on the victim machine. The stated impact includes high confidentiality, integrity, and availability consequences.