ShellCodeX
Tools • Events • News • Insights
SEO Checker
ShellCodeX vulnerability brief
MEDIUM Received

CVE-2026-75130

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.

Published 18 Aug 2026, 18:19 UTC Last modified 18 Aug 2026, 18:19 UTC
01

Attack profile

The conditions required to exploit this vulnerability and its potential impact.

Attack vector Network
Attack complexity Low
Privileges required Low
User interaction Passive
Scope Not assessed
Confidentiality Not assessed
Integrity Not assessed
Availability Not assessed
02

Affected products

Product applicability statements supplied with the NVD record.

NVD has not published structured affected-product data for this record.
03

Weakness classification

CWE categories help security teams group the underlying software weakness.

Weakness classification is still awaiting analysis.
04

Source references

External advisories, patches and technical reports attached to this CVE record.