CVE-2026-75130 - Context7 2.1.2 Prompt Injection via Custom AI Instructions
Brief
CVE ID : CVE-2026-75130
Published : Aug. 18, 2026, 6:19 p. m.
- 48 minutes ago
Description : Context7 through 2.
- 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.
Severity: 9.0
- CRITICAL
Visit the link for more details, such as CVSS details, affected products, timeline, and more...