Vulnerability · Published Aug 18, 2026 · Assigned by VulnCheck

CVE-2026-75130Context7 2.1.2 Prompt Injection via Custom AI Instructions

Critical 9.0

In plain English

A critical-severity security flaw in Context7 from Uptash. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 42% of all known vulnerabilities).

Severity (CVSS 3.1)9.0Critical

Exploit odds (30 days)0.5%top 57.7% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected products (as reported)

Vendor	Product	Versions
Uptash	Context7	0 – through 2.1.2

Weakness: CWE-1427 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H

References

Noma Security Blog technical-description, exploit
Supplier LinkedIn Post vendor-advisory
https://www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructions third-party-advisory