# mcp-sanitizer: URL sanitizer allows localhost/IPv6 loopback SSRF bypass via explicit port or bracketed IPv6

Advisory record · `GHSA-4mfg-r38w-w8fg`

- **Identifiers:** `GHSA-4mfg-r38w-w8fg`
- **State:** Confirmed
- **Severity:** CVSS 8.2 High
- **Critical:** No
- **Weakness (CWE):** [CWE-918](https://cwe.mitre.org/data/definitions/918.html)
- **Tags:** [Server-side request forgery (SSRF)](https://agentprime.io/advisories/tag/ssrf.md)
- **Published:** 28 Oct 2026
- **Updated:** 28 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 28 Oct 2026, 19:51 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `mcp-sanitizer` (npm): affected `<1.4.0`; fixed in `1.4.0`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> The mcp-sanitizer npm package, versions before 1.4.0, has a URL validation gap in which localhost URLs with an explicit port and bracketed IPv6 loopback or link-local addresses are not blocked, allowing server-side request forgery. An unauthenticated attacker who can supply the URL parameter of a web_fetch or web_scraper tool can get the sanitizer to approve internal targets, potentially reading responses from internal services. The fix is to upgrade to version 1.4.0.

Written 31 Oct 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 8.2 High, CVSS 3.1: `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N`, from GitHub Advisory Database

- **CISA KEV:** Not listed.
- **EPSS:** No score.

## Timeline

- 31 Oct 2026, 13:33 UTC: First seen by agentprime
- 31 Oct 2026, 13:33 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-4mfg-r38w-w8fg)

## Sources

- [GitHub Advisory Database: GHSA-4mfg-r38w-w8fg](https://github.com/advisories/GHSA-4mfg-r38w-w8fg)
- [OSV: GHSA-4mfg-r38w-w8fg](https://osv.dev/vulnerability/GHSA-4mfg-r38w-w8fg)
- <https://github.com/starman69/mcp-sanitizer/security/advisories/GHSA-4mfg-r38w-w8fg>
- <https://github.com/starman69/mcp-sanitizer/commit/200685889b073f7470859b0941b67b7f46255f09>
- <https://github.com/starman69/mcp-sanitizer>
- <https://github.com/starman69/mcp-sanitizer/releases/tag/v1.4.0>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-4mfg-r38w-w8fg>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-4mfg-r38w-w8fg/>. Everything for agents: <https://agentprime.io/llms.txt>.