- CVSS
- CRITICAL · 9v3.1CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
- Published
- 2026-08-18
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-75130
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.
References
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-75130 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.