# mcp-contextforge-gateway has Server-Side Template Injection (SSTI) leading to Remote Code Execution in \`PromptService.\_render_template\` via unsandboxed Jinja2 Environment

Advisory record · `GHSA-vwf3-4xxj-qg6h`

- **Identifiers:** `GHSA-vwf3-4xxj-qg6h`
- **State:** Confirmed
- **Severity:** No CVSS score
- **Critical:** No
- **Weakness (CWE):** [CWE-94](https://cwe.mitre.org/data/definitions/94.html) · [CWE-1336](https://cwe.mitre.org/data/definitions/1336.html)
- **Tags:** [Code injection](https://agentprime.io/advisories/tag/code-injection.md)
- **Published:** 25 Aug 2026
- **Updated:** 26 Aug 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 25 Aug 2026, 17:42 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `mcp-contextforge-gateway` (PyPI): affected `<1.0.0`; fixed in `1.0.0`

## Machine-written summary

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

> mcp-contextforge-gateway versions before 1.0.0 render user-supplied prompt templates with an unsandboxed Jinja2 environment. An authenticated user allowed to create or update prompts can store a template that runs arbitrary Python code on the gateway host. Upgrade to version 1.0.0 or later.

Written 5 Nov 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

No source has published a CVSS score for this record yet.

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

## Timeline

- 31 Oct 2026, 14:39 UTC: First seen by agentprime
- 31 Oct 2026, 14:39 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-vwf3-4xxj-qg6h)

## Sources

- [GitHub Advisory Database: GHSA-vwf3-4xxj-qg6h](https://github.com/advisories/GHSA-vwf3-4xxj-qg6h)
- [OSV: GHSA-vwf3-4xxj-qg6h](https://osv.dev/vulnerability/GHSA-vwf3-4xxj-qg6h)
- <https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-vwf3-4xxj-qg6h>
- <https://github.com/IBM/mcp-context-forge/issues/538>
- <https://github.com/IBM/mcp-context-forge/pull/4072>
- <https://github.com/IBM/mcp-context-forge/commit/4d31004661858a2e99055b3c0c9f14218b8f7120>
- <https://github.com/IBM/mcp-context-forge>
- <https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.0>

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-vwf3-4xxj-qg6h>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-vwf3-4xxj-qg6h/>. Everything for agents: <https://agentprime.io/llms.txt>.