Description
A vulnerability exists in the Kong Konnect Model Context Protocol (MCP) server prior to version 1.0.0, which could allow a remote attacker to perform an indirect prompt injection attack and execute unintended API requests.
Published: 2026-07-03
Score: 7.4 High
EPSS: < 1% Very Low
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Impact

A flaw in the Kong Konnect Model Context Protocol (MCP) server before version 1.0.0 permits a remote attacker to manipulate untrusted analytics data, resulting in an indirect prompt injection that can cause unintended API requests. This input‑validation weakness, classified as CWE‑20, may affect the intended request flow on the MCP service.

Affected Systems

All Kong Konnect MCP deployments running any release prior to 1.0.0 are vulnerable. The issue lies in the component that processes incoming analytics payloads from external sources, so any installation that accepts such data without strict validation can be affected.

Risk and Exploitability

The vulnerability carries a CVSS score of 7.4, indicating high severity, while an EPSS score of less than 1% indicates a low likelihood of exploitation. Based on the description, the likely attack vector is remote; an adversary would need to send crafted analytics payloads to the MCP service. Although the vulnerability is not listed in the CISA KEV catalog and no active exploits are reported, the potential for unintended API requests warrants attention.

Generated by OpenCVE AI on July 31, 2026 at 14:50 UTC.

Remediation

No vendor fix or workaround currently provided.

OpenCVE Recommended Actions

  • Upgrade Kong Konnect MCP to version 1.0.0 or later to eliminate the input‑validation flaw.
  • Restrict analytics ingestion to trusted, internally generated sources, blocking any untrusted payloads from reaching the MCP service.
  • Implement strict input validation or sanitization on the MCP endpoints to reject malformed or unexpected prompt data, addressing the CWE‑20 weakness.
  • If an immediate upgrade is not possible, temporarily disable the analytics ingestion feature until a patch is applied.
  • Continuously monitor MCP logs for abnormal API request patterns that may indicate attempted prompt injection or credential abuse.

Generated by OpenCVE AI on July 31, 2026 at 14:50 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Mon, 06 Jul 2026 23:15:00 +0000

Type Values Removed Values Added
First Time appeared Konghq
Konghq mcp-konnect
Vendors & Products Konghq
Konghq mcp-konnect

Mon, 06 Jul 2026 18:30:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Fri, 03 Jul 2026 11:00:00 +0000

Type Values Removed Values Added
Description A vulnerability exists in the Kong Konnect Model Context Protocol (MCP) server prior to version 1.0.0, which could allow a remote attacker to perform an indirect prompt injection attack and execute unintended API requests.
Title Prompt Injection and Credential Exposure via Untrusted Analytics Data in Kong Konnect MCP
Weaknesses CWE-20
References
Metrics cvssV3_1

{'score': 7.4, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:N/A:N'}

Subscriptions

Konghq Mcp-konnect
cve-icon MITRE

Status: PUBLISHED

Assigner: Kong

Published:

Updated: 2026-07-06T17:29:24.789Z

Reserved: 2026-06-25T14:11:55.561Z

Link: CVE-2026-13341

cve-icon Vulnrichment

Updated: 2026-07-06T17:29:21.554Z

cve-icon NVD

Status : Awaiting Analysis

Published: 2026-07-03T11:16:27.720

Modified: 2026-07-06T19:01:56.880

Link: CVE-2026-13341

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-07-31T15:00:04Z

Weaknesses
  • CWE-20

    Improper Input Validation