CVE-2026-75130
Context7 2.1.2 Prompt Injection via Custom AI Instructions
CVSS Score
9.0
EPSS Score
0.0%
EPSS Percentile
0th
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.
| CWE | CWE-1427 |
| Vendor | uptash |
| Product | context7 |
| Published | Aug 18, 2026 |
| Last Updated | Aug 18, 2026 |
Stay Ahead of the Next One
Get instant alerts for uptash context7
Be the first to know when new critical vulnerabilities affecting uptash context7 are published — delivered to Slack, Telegram or Discord.
Get Free Alerts →
Free · No credit card · 60 sec setup
CVSS v3 Breakdown
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
Required
Scope
Changed
Confidentiality
High
Integrity
High
Availability
High
Affected Versions
Uptash / Context7
0 ≤ 2.1.2
References
noma.security: https://noma.security/blog/contextcrush-context7-the-mcp-server-vulnerability/ linkedin.com: https://www.linkedin.com/posts/upstash_mcp-server-vulnerability-in-context-7-activity-7435686676049387520-PBVo/ vulncheck.com: https://www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructions
Credits
Eli Ainhorn - Senior AI Vulnerability Researcher @ Noma Security