CVE-2026-18655 Broker Credential and OAuth Token Disclosure in AWS Labs Amazon MQ MCP Server via Prompt Injection

HighCVSS 7.1 EPSS 0.42%

Published: 2026-08-03 22:04
Updated: 2026-10-24 00:10
Exploit status: No public exploit known

Description

Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server (awslabs.amazon-mq-mcp-server) before 2.0.24 may allow a remote unauthenticated actor (via prompt injection) to obtain Amazon MQ for RabbitMQ broker credentials or OAuth access tokens sent to a crafted endpoint controlled through a broker hostname introduced in the MCP client context.

To remediate this issue, users should upgrade to version 2.0.24.

Affected products

Product	Affected versions	Fixed in
AWS amazon-mq-mcp-server	<= 2.0.23	No fix listed

References

pypi.org patch release-notes
aws.amazon.com vendor-advisory
github.com release-notes

CVSS v4.0

7.1 High

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N

Attack Vector: Network
Attack Complexity: Low
Attack Requirements: None
Privileges Required: None
User Interaction: Passive
Vulnerable System Confidentiality: High
Vulnerable System Integrity: None
Vulnerable System Availability: None
Subsequent System Confidentiality: None
Subsequent System Integrity: None
Subsequent System Availability: None

All scores (4)

v4.0 7.1 · amzn
v4.0 7.1 · ff89ba41-3aa1-4d27-914a-91399e9639e5
v3.1 6.5 · amzn
v3.1 6.5 · ff89ba41-3aa1-4d27-914a-91399e9639e5

Weakness & likelihood

EPSS (exploitation probability, 30 days): 0.42% (percentile 37.1)
CWE: CWE-923 Improper Restriction of Communication Channel to Intended Endpoints

Public exploit references

Metadata only. CVERadar never hosts or runs exploit code.

No public exploit references known.