Prompt Injection Vulnerability in Context7 by Noma Security
CVE-2026-75130

6.4MEDIUM

Key Information:

Vendor

Uptash

Status
Context7
Vendor
CVE Published:
18 August 2026

Badges

👾 Exploit Exists🟡 Public PoC

What is CVE-2026-75130?

The vulnerability in Context7, specifically version 2.1.2, allows attackers to perform prompt injection through the Custom AI Instructions feature. By injecting unsanitized content via the MCP server, adversaries can manipulate AI coding agents to execute harmful instructions. This exploitation enables attackers to exfiltrate sensitive credentials from environment files to unauthorized services and initiate destructive file deletions during routine library documentation requests by the affected agents.

Affected Version(s)

Context7 0 <= 2.1.2

Exploit Proof of Concept (PoC)

PoC code is written by security researchers to demonstrate the vulnerability can be exploited. PoC code is also a key component for weaponization which could lead to ransomware.

CVE-2026-75130 - Proof of Concept

References

https://noma.security/blog/contextcrush-context7-the-mcp-...
technical-descriptionexploit
https://www.linkedin.com/posts/upstash_mcp-server-vulnera...
vendor-advisory
https://www.vulncheck.com/advisories/context7-prompt-inje...
third-party-advisory

CVSS V4

Score:
6.4
Severity:
MEDIUM
Confidentiality:
None
Integrity:
None
Availability:
None
Attack Vector:
Network
Attack Complexity:
Low
Attack Required:
None
Privileges Required:
Undefined
User Interaction:
Unknown

Timeline

  • 🟡

    Public PoC available

  • 👾

    Exploit known to exist

  • Vulnerability published

  • Vulnerability Reserved

Credit

Eli Ainhorn - Senior AI Vulnerability Researcher @ Noma Security
.