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

> Attackers can inject malicious instructions via Context7 to exfiltrate credentials and delete files on victim machines through AI coding agents.

- **Severity:** Medium 6.4 (`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`)
- **Exploited in the wild:** Not known
- **Login needed:** Any signed-in user
- **Attackable:** Over the internet
- **Victim action needed:** A user has to click or open something
- **Fix available:** No
- **Published:** 18 Aug 2026
- **Updated:** 19 Aug 2026
- **Also known as:** GHSA-97r6-3rgm-v39r

## What is CVE-2026-75130?

CVE-2026-75130 is a medium-severity code injection vulnerability in Uptash Context7, published on 18 Aug 2026. Any signed-in user can exploit it over the network, and only if a user opens a file or follows a link.

### Official 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.

Weakness: CWE-1427 (Improper Neutralization of Input Used for LLM Prompting)

## Which versions are affected by CVE-2026-75130?


## How do I fix CVE-2026-75130?

No fix has been published for CVE-2026-75130 yet. Limit exposure of the affected software until one is available.

## Is CVE-2026-75130 being exploited?

There is no known exploitation of CVE-2026-75130 in the wild and no public exploit code.

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-75130 and fix it if it is affected.

What it is: CVE-2026-75130 is a medium-severity code injection vulnerability in Uptash Context7, published on 18 Aug 2026. Any signed-in user can exploit it over the network, and only if a user opens a file or follows a link.
Exploitation: There is no known exploitation of CVE-2026-75130 in the wild and no public exploit code.

Affected product: Uptash Context7. No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-75130/ (Markdown: https://insights.sbomify.com/CVE-2026-75130/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-75130
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-75130
- OSV: https://osv.dev/vulnerability/CVE-2026-75130

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-75130/
Summaries are generated and may contain mistakes; the official description above is the record.