by Kastro
Paper/Archive/CVE-2026-75130

CVE-2026-75130

Uptash Context7 — Context7 2.1.2 Prompt Injection via Custom AI Instructions

EPSS 0.5%CVSS 9.0
critical.is priorityof 100
35
CVSS 9.0 (CNA)9.0 / 10 × 3027.0Not in CISA KEV+300.0EPSS percentile 42.1.421 × 208.4No public exploit+100.0SSVC exploitation: none+100.0
Description · from the CVE record

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.

Affected

ProductAffectedFixed inSource
Context7≤ 2.1.2–CNA

Scores by source

VulnCheck (CNA)9.0CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
VulnCheck (CNA)6.4CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:N/VI:N/VA:N/SC:H/SI:H/SA:H
CISA ADPSSVCExploitation: none · Automatable: no · Technical impact: total

References

exploitnoma.security/blog/contextcrush-context7-the-mcp-server-vulnerabilityadvisorylinkedin.com/posts/upstash_mcp-server-vulnerability-in-context-7-activity-7435686676049387520-PBVowriteupvulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructions