CVE-2026-75130

medium

Description

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.

References

https://www.linkedin.com/posts/upstash_mcp-server-vulnerability-in-context-7-activity-7435686676049387520-PBVo/

https://noma.security/blog/contextcrush-context7-the-mcp-server-vulnerability/

https://www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructions

https://euvd.enisa.europa.eu/vulnerability/EUVD-2026-61099

Details

Source: Mitre, NVD

Published: 2026-08-18

Updated: 2026-09-24

Risk Information

CVSS v2

Base Score: 9

Vector: CVSS2#AV:N/AC:L/Au:S/C:C/I:C/A:C

Severity: High

CVSS v3

Base Score: 9

Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H

Severity: Critical

CVSS v4

Base Score: 6.4

Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:N/VI:N/VA:N/SC:H/SI:H/SA:H

Severity: Medium

EPSS

EPSS: 0.00276