Find notable cyber news and cases, enriched with sources, timelines, and signals.
Home Watchlists Beta Browse News Feed Stats About Contact

Amazon Kiro IDE prompt injection data exfiltration security flaw

Vulnerability
First reported
Last updated
Happening score
H score 28
1 unique sources, 1 articles

Summary

Hide ▲

Amazon Kiro IDE 0.7.45 on Windows was found to have a prompt injection vulnerability that let attacker-controlled repository content influence Kiro Powers and push sensitive local information to an external endpoint. The flaw enabled data exfiltration after a victim opened a malicious workspace file and sent a message, even without explicitly asking Kiro to access or transmit the data. Amazon released a fix in Kiro IDE 0.8.140 after responsible disclosure.

Related Happenings

Kiro prompt-injection config rewrite RCE remote code execution flaw

Vulnerability
H score31 First: 21.07.2026 19:06 Last: 21.07.2026 19:06 Sources 1

About this happening: AWS Kiro had a prompt-injection RCE vulnerability that let hidden web text rewrite ~/.kiro/settings/mcp.json and launch attacker-controlled code on a developer machine...

Open Happening

Checkmarx/kics Docker Hub repository hit by network compromise

Incident
H score36 First: 22.04.2026 20:55 Last: 22.04.2026 20:55 Sources 1

About this happening: Checkmarx's checkmarx/kics Docker Hub repository suffered a supply-chain compromise that could expose secrets from infrastructure-as-code scans. Unknown threat actor...

Open Happening

Cline AI coding assistant hit by network compromise

Incident
H score18 First: 09.03.2026 01:35 Last: 09.03.2026 01:35 Sources 1

About this happening: The Cline coding assistant suffered a supply-chain compromise that installed a rogue OpenClaw instance on thousands of systems, creating unauthorized full system...

Open Happening

Timeline

  1. 27.08.2026 16:39 2 articles · 6h ago

    Amazon Kiro IDE prompt injection flaw can exfiltrate sensitive local data

    Initial Disclosure

    Cybersecurity researchers disclosed a prompt injection flaw in Amazon Kiro IDE 0.7.45 on Windows that let attacker-controlled repository content influence Kiro Powers and transmit sensitive local information to an external endpoint after a victim opened a crafted workspace file and sent any message. Mindguard said the issue was reproducible in both trusted and untrusted workspaces, had low exploitation difficulty, and Amazon implemented a fix in Kiro IDE version 0.8.140.

    Show sources
    Open in new tab