CVE-2026-75130

Published: Ago 18, 2026 Last Modified: Ago 19, 2026
ExploitDB:
Other exploit source:
Google Dorks:
MEDIUM 6,4
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: passive
Confidentiality: N/A
Integrity: N/A
Availability: N/A
CRITICAL 9,0
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: required
Scope: changed
Confidentiality: high
Integrity: high
Availability: high

Description

AI Translation Available

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.

https://noma.security/blog/contextcrush-context7-the-mcp-server-vulnerability/
https://www.linkedin.com/posts/upstash_mcp-server-vulnerability-in-context-7-ac…
https://www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-in…