CVE-2026-75130
Context7 2.1.2 Prompt Injection via Custom AI Instructions
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.
INFO
Published Date :
Aug. 18, 2026, 6:19 p.m.
Last Modified :
Oct. 22, 2026, 10:10 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | CRITICAL | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 3.1 | CRITICAL | [email protected] | ||||
| CVSS 3.1 | CRITICAL | MITRE-CVE | ||||
| CVSS 4.0 | MEDIUM | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 4.0 | MEDIUM | [email protected] |
Solution
- Sanitize all user-provided custom instructions.
- Implement strict input validation for AI interactions.
- Update the MCP server to the latest version.
- Review agent interactions for suspicious activity.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-75130.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-75130 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-75130
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-75130 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-75130 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Translated by [email protected]
Oct. 22, 2026
Action Type Old Value New Value Added Translation Title: Context7 de Uptash, Description: Context7 hasta 2.1.2 contiene una vulnerabilidad de inyección de prompt que permite a los atacantes ejecutar instrucciones maliciosas en agentes de codificación de IA conectados inyectando contenido no sanitizado a través de la función de Instrucciones de IA Personalizadas servida a través del servidor MCP. Los atacantes pueden envenenar las instrucciones personalizadas para exfiltrar credenciales de archivos de entorno a un servicio controlado por el atacante y realizar la eliminación destructiva de archivos en la máquina de la víctima cuando el agente realiza una solicitud rutinaria de documentación de la biblioteca. -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Aug. 19, 2026
Action Type Old Value New Value Added SSVC {'id': 'CVE-2026-75130', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'none'}, {'automatable': 'no'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-08-19T15:14:18.244695Z'} -
New CVE Received by [email protected]
Aug. 18, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'Uptash', 'product': 'Context7', 'versions': [{'status': 'affected', 'version': '0', 'versionType': 'semver', 'lessThanOrEqual': '2.1.2'}], 'defaultStatus': 'affected'}] Added 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. Added CVSS V4.0 AV:N/AC:L/AT:N/PR:L/UI:P/VC:N/VI:N/VA:N/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Added CVSS V3.1 AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H Added Reference https://noma.security/blog/contextcrush-context7-the-mcp-server-vulnerability/ Added Reference https://www.linkedin.com/posts/upstash_mcp-server-vulnerability-in-context-7-activity-7435686676049387520-PBVo/ Added Reference https://www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructions