# dbt MCP Server has an Argument Injection in dbt CLI Tool Wrappers via node_selection and resource_type Parameters

Advisory record · `GHSA-xpww-f6pm-cfhq`

- **Identifiers:** `GHSA-xpww-f6pm-cfhq` · `CVE-2026-44968` · `PYSEC-2026-2444`
- **State:** Confirmed
- **Severity:** CVSS 6.3 Medium
- **Critical:** No
- **Weakness (CWE):** [CWE-88](https://cwe.mitre.org/data/definitions/88.html)
- **Tags:** [Command injection](https://agentprime.io/advisories/tag/command-injection.md)
- **Published:** 14 May 2026
- **Updated:** 13 Jul 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 14 May 2026, 18:24 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `dbt-mcp` (PyPI): affected `<1.17.1`; fixed in `1.17.1`

## Machine-written summary

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

> The dbt MCP Server (PyPI package dbt-mcp) before 1.17.1 passes user-supplied tool parameters into dbt CLI argument lists without validation. An MCP client able to call the affected tools (such as build, run, test, or list) can inject dbt global flags like --profiles-dir, --project-dir, and --target through the node_selection or resource_type parameters. Upgrade to dbt-mcp 1.17.1 or later. The source gives no workaround beyond upgrading.

Written 6 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

- 6.3 Medium, CVSS 3.1: `CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:N`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0021, the 10th percentile, on 15 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 15:02 UTC: First seen by agentprime
- 31 Oct 2026, 15:02 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-xpww-f6pm-cfhq)

## Sources

- [GitHub Advisory Database: GHSA-xpww-f6pm-cfhq](https://github.com/advisories/GHSA-xpww-f6pm-cfhq)
- [OSV: GHSA-xpww-f6pm-cfhq](https://osv.dev/vulnerability/GHSA-xpww-f6pm-cfhq)
- <https://github.com/dbt-labs/dbt-mcp/security/advisories/GHSA-xpww-f6pm-cfhq>
- <https://github.com/dbt-labs/dbt-mcp>
- <https://github.com/dbt-labs/dbt-mcp/releases/tag/v1.17.1>

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-xpww-f6pm-cfhq>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-xpww-f6pm-cfhq/>. Everything for agents: <https://agentprime.io/llms.txt>.
