MEDIUMAi
Global

Amazon Q Developer Flaw Could Let Malicious Repos Run Code via MCP Configs

·Source: The Hacker News

Updated:

Executive Summary

A high-severity flaw in Amazon Q Developer let a malicious repository run commands and steal a developer's cloud credentials. The path was short: a developer opens the repo, trusts the workspace, and Amazon Q does the rest. Amazon has patched it. Tracked as CVE-2026-12957 (CVSS 8.5), the bug sat in how Amazon's AI coding assistant handled Model Context Protocol (MCP) servers. Wiz

Analysis

A high-severity flaw in Amazon Q Developer let a malicious repository run commands and steal a developer's cloud credentials. The path was short: a developer opens the repo, trusts the workspace, and Amazon Q does the rest. Amazon has patched it. Tracked as CVE-2026-12957 (CVSS 8.5), the bug sat in how Amazon's AI coding assistant handled Model Context Protocol (MCP) servers. Wiz

Indicators of Compromise (1)

CVE (1)
CVE-2026-12957
NVDMITRE CVE
Source Attribution

Originally published by The Hacker News on Jun 26, 2026.

Related Threats

MEDIUMAi

OCBC adds AI-powered financial advisor avatars to app

OCBC has revamped its mobile app with two AI-powered avatars that deliver "hyper-personalised" wealth management services in real-time 24 hours a day.

Finextra
MEDIUMAi

SoFi buys AI-based investing startup Composer

US fintech SoFi has acquired Composer, a Toronto-based AI-powered retail investing startup. Financial terms were not disclosed.

Finextra
MEDIUMAi

Prohibiting AI Use Increases Enterprise Data Risk

<img src="https://ismg-cdn.nyc3.cdn.digitaloceanspaces.com/articles/prohibiting-ai-use-increases-enterprise-data-risk-image_small-9-a-32124.jpg" align=right hspace=4><b>Fortra's Tony Kelly on Securing AI Adoption With Governance, Data Protection</b><br>Organizations that block generative AI use often create greater security risks by driving employees toward unauthorized tools, said Tony Kelly, reg

Bank Info Security