VulnWatch VulnWatch
← Back to dashboard
Medium github · GHSA-83x6-42hr-jc76

CKAN MCP Server: MQA server allowlist bypass via unanchored regex (`isValidMqaServer`)

Published Sep 2, 2026 CVSS 5.3

Summary

The ckan_get_mqa_quality and ckan_get_mqa_quality_details tools restrict their server_url argument to dati.gov.it via a regular expression. The regex is anchored only at the start and places no boundary after the host, so any URL whose host merely begins with dati.gov.it — or that uses dati.gov.it as URL userinfo before an @ — passes validation while actually targeting an attacker-controlled host.

Affected code

// src/tools/quality.ts
const ALLOWED_SERVER_PATTERNS = [
  /^https?:\/\/(www\.)?dati\.gov\.it/i        //  pattern.test(serverUrl));
}

All of the following return true:

URL Real host
https://dati.gov.it.attacker.com/x dati.gov.it.attacker.com (attacker)
http://dati.gov.it.evil.example/api dati.gov.it.evil.example (attacker)
https://[email protected]/x attacker.com (userinfo trick)

After passing this check, server_url flows into getMqaQuality/getMqaQualityDetails, which call makeCkanRequest(serverUrl, "package_show", { id }). The server therefore issues a request to the attacker-controlled host and returns its (parsed) response to the caller.

Impact

  • The intended "dati.gov.it only" trust boundary for the MQA tools is defeated; they can be driven against arbitrary external hosts.
  • The attacker host receives the request (including the dataset_id) and controls the response body that is surfaced back to the model/user — enabling response spoofing and, in an agentic setting, indirect prompt-injection content delivered under the guise of a trusted-portal tool.
  • Contributes to SSRF surface: while makeCkanRequest blocks private/internal IPs, this bypass removes the domain restriction that the code intends to enforce for these tools.

The @-userinfo variant is the most severe form because validation passes on a string whose actual host is fully attacker-chosen.

Proof of concept

poc/mqa-allowlist-poc.mjs runs the verbatim regex over benign and malicious URLs:

accepted  expected_legit  url
true      true            https://dati.gov.it/opendata

Affected AI Products

indirect prompt mcp server agentic
Get the weekly digest. Every Monday: top AI security stories of the week. Free.