Vulnerability in Uptash Context7
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 · last modified .
CVSS v3 metric
CVSS v3 base score 9.0 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H.
EPSS exploit prediction
EPSS: 0.005 (39.9th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 40th percentile — 39.9% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.003 · newest: 0.005 · change: +0.002
Affected products
Weakness classification (CWE)
References
- noma.security/blog/contextcrush-context7-the-mcp-server-vulnerability/ (technical-description, exploit)
- www.linkedin.com/posts/upstash_mcp-server-vulnerability-in-context-7-activity-7… (vendor-advisory)
- www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructio… (third-party-advisory)
Frequently asked questions
- What is CVE-2026-75130?
- CVE-2026-75130 is a critical-severity vulnerability in Uptash Context7, classified under CWE-1427. CVSS score: 9.0/10. Published 2026-08-18.
- How severe is CVE-2026-75130?
- Critical severity. CVSS v3 base score is 9.0 out of 10.