CVE-2026-75130
6.4
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:N/VI:N/VA:N/SC:H/SI:H/SA:H
Summary
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 Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| Uptash | Context7 | 0 <= 2.1.2 | affected |
Weaknesses
- CWE-1427: Improper Neutralization of Input Used for LLM Prompting
References
- https://noma.security/blog/contextcrush-context7-the-mcp-server-vulnerability/
- https://www.linkedin.com/posts/upstash_mcp-server-vulnerability-in-context-7-activity-7435686676049387520-PBVo/
- https://www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructions
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.