Skip to main content
Press slash or control plus K to focus the search. Use the arrow keys to navigate results and press enter to open a threat.
Reconnecting to live updates…

CVE-2026-85788: CWE-184 Incomplete list of disallowed inputs in AWS AWS Labs MySQL MCP Server

0
Medium
VulnerabilityCVE-2026-85788cvecve-2026-85788cwe-184cloud
Published: 09/09/2026 (09/09/2026, 16:32:59 UTC)
Source: CVE Database V5
Vendor/Project: AWS
Product: AWS Labs MySQL MCP Server

Description

CVE-2026-85788 is a medium-severity vulnerability in AWS Labs MySQL MCP Server (an open-source, self-hosted Model Context Protocol server). The issue allows circumvention of the read-only enforcement via SQL inline comments under certain conditions, potentially permitting execution of statements that should be blocked. This vulnerability affects versions up to and including 1.0.21. The read-only mode is a best-effort safeguard and does not replace proper database permissions. The vulnerability does not impact the confidentiality or integrity of any AWS service. AWS manages remediation for this cloud-hosted service, and a patch is available.

CVSS v3.1

Score 5.5medium

Attack Vector
Local
Attack Complexity
Low
Privileges Required
None
User Interaction
Required
Scope
Unchanged
Confidentiality
High
Integrity
None
Availability
None
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N

Affected software

GitHub Actionsmore threats →ai
awslabs/mcp
pkg:github/awslabs/mcp
Affected versions
<=1.0.21

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 09/09/2026, 16:45:11 UTC

Technical Analysis

The vulnerability identified as CVE-2026-85788 involves an incomplete list of disallowed inputs in the AWS Labs MySQL MCP Server's read-only enforcement mechanism. Specifically, SQL inline comments can be used to bypass the read-only check, allowing execution of statements that the server intended to block. This issue affects awslabs.mysql-mcp-server versions up to and including 1.0.21. The read-only mode is a best-effort feature and relies on the permissions of the configured MySQL user. The vulnerability does not affect AWS service confidentiality or integrity. AWS provides this server as a client-side, self-managed package, and customers control installation and database credential privileges. AWS manages remediation for this cloud-hosted service, and a patch is available as per the vendor advisory.

Potential Impact

The vulnerability allows bypassing the read-only enforcement in the AWS Labs MySQL MCP Server, potentially enabling execution of SQL statements that should be blocked. However, the impact is limited because the read-only mode is a best-effort safeguard and the effective security boundary is the permissions of the configured MySQL user. There is no impact on the confidentiality or integrity of AWS services. The vulnerability is rated medium severity with a CVSS score of 5.5.

Mitigation Recommendations

A patch is available for this vulnerability. Since this is a client-side, self-managed package, customers should update awslabs.mysql-mcp-server to a version later than 1.0.21 where the issue is fixed. AWS manages remediation for this cloud-hosted service; customers should refer to the official AWS Security Bulletin at https://aws.amazon.com/security/security-bulletins/2026-103-aws/ for the most current remediation guidance.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
AMZN
Date Reserved
2026-09-04T17:19:34.906Z
Cvss Version
3.1
State
PUBLISHED
Remediation Level
null
Is Cloud Service
true
Vendor Advisory Urls
[{"url":"https://aws.amazon.com/security/security-bulletins/2026-103-aws/","vendor":"AWS"}]

Threat ID: 6aa18b79acd9273b4996dce1

Added to database: 09/09/2026, 16:38:17 UTC

Last enriched: 09/09/2026, 16:45:11 UTC

Last updated: 09/09/2026, 17:01:53 UTC

Views: 6

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses