CVE-2026-75130

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.

CVSS v4.0

6.4 MEDIUMCVSS:4.0/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

CVSS v3.1

9.0 CRITICALCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H

EPSS

0.28% chance of exploitation in the next 30 days, 20th percentile

Published

2026-08-18

Updated

2026-08-19

Proof-of-concept exploits (1)

• https://noma.security/blog/contextcrush-context7-the-mcp-server-vulnerability/

References

• CVE Record
• NVD entry

Related

• CVE-2026-7513
• CVE-2026-7515
• CVE-2026-7512
• CVE-2026-7518
• CVE-2026-7510
• CVE-2026-7519