BaselineWatch
Desk

CVE-2026-75130

6.4 medium SSVC exploitation: none Deferred

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.

Fix

Nothing published yet: no patch, vendor advisory or mitigation reference on NVD, no vendor advisory in the News for this CVE, not in CISA's KEV, no fixed package version. BaselineWatch does not guess at one.

Change history 1

  1. First seenCVSS 6.4NVD modified 2026-10-22 22:10

Affected (CPE criteria) 0

NVD has not attached CPE configurations yet.

References 3