CVE-2026-75130
Context7 2.1.2 Prompt Injection via Custom AI Instructions
- State
- Published
- Severity
- 6.4 Medium
- Published
- Aug 18, 2026
- Updated
- Aug 19, 2026
- Reserved
- Aug 17, 2026
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 4.0 | 6.4 Medium | 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 | VulnCheck |
| 3.1 | 9.0 Critical | CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H | VulnCheck |
Weaknesses
- CWE-1427 Improper Neutralization of Input Used for LLM Prompting
Affected Products
| Product | Versions |
|---|---|
Context7Uptash |
|
References
- Noma Security Blogtechnical-descriptionexploit
- Supplier LinkedIn Postvendor-advisory
- https://www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructionsthird-party-advisory
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.