AI Weekly Malaysia

Back to items Summaries

Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers

ID
18677
Status
summarized
Published
27 Aug 2026, 9:39 PM
Fetched
28 Aug 2026, 5:26 PM
Provider
The Hacker News
Category
security
Original URL
https://thehackernews.com/2026/08/amazon-kiro-prompt-injection-can.html
Source URL
https://feeds.feedburner.com/TheHackersNews

Summary

Score
6.5
Created
28 Aug 2026, 5:26 PM
Tags
Audience
developersai_agent_usersai_ml_learners

What happened

Mindguard disclosed a prompt injection vulnerability in Amazon Kiro IDE (version 0.7.45 on Windows) that lets attacker-controlled repository content exfiltrate sensitive local data via Kiro Powers. Exploitation requires the user to open a malicious project via File → Open Workspace From File and then send any message to the agent—no malicious prompt needed. The latest IDE version is 1.0.337, and no CVE has been assigned.

Why it matters

If you or your team use Amazon Kiro, update to 1.0.337 immediately and stop opening workspace files from untrusted repos via File → Open Workspace From File. The attack chain is notable because it requires no crafted prompt—just opening the workspace and sending any message triggers exfiltration through Kiro Powers' MCP server configs and steering files.

Discussion angle

This is a concrete example of how agentic IDEs that auto-load MCP configs and steering files from repo content create a trust boundary problem—discuss whether your team's AI coding tools have equivalent risks and what review process you apply before opening third-party projects.

Top