CVE-2026-75130 Context7 2.1.2 Prompt Injection via Custom AI Instructions
MediumCVSS 6.4
EPSS 0.49%
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- No known exploitation · automatable: no · technical impact: total
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.
Upgrade path
1 package: 1 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| Uptash Context7 | <= 2.1.2 | after 2.1.2 | Fixed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| Uptash Context7 | <= 2.1.2 | No fix listed |
References
- Noma Security Blog exploit technical-description
- Supplier LinkedIn Post vendor-advisory
- www.vulncheck.com third-party-advisory
- ENISA EUVD EUVD-2026-61099 third-party-advisory