Executive Summary
Mindgard disclosed a Kiro IDE 0.7.45 (Windows) flaw without a CVE where prompt injection could exfiltrate sensitive data via Kiro Powers.
What Happened
Cybersecurity researchers have disclosed details of a vulnerability in Amazon Kiro, an artificial intelligence (AI)-powered, agentic integrated development environment (IDE), that could facilitate data exfiltration via prompt injection and Kiro Powers. The security flaw, which does not have a CVE identifier, works against Kiro IDE 0.7.45 on Windows, according to Mindgard. The latest version of
Affected Products
- Amazon Kiro 0.7.45
Vulnerability / Attack Technique
Prompt injection leading to data exfiltration
Technical Mechanism
Injected instructions in content the IDE agent processes caused it to send data out through Kiro Powers.
AI Security Category
LLM01:2025 Prompt Injection
Part of the Prompt Injection topic.
Relevant Frameworks
RealGround Analysis
The same Kiro exfiltration path, at the source. RealGround analysis: keep agentic IDEs updated and egress-restricted.
Recommended Controls
- Update Kiro beyond 0.7.45
- Restrict agentic IDE network access
Related RealGround Service
Secure AI Agent Build · or start with the free AI Agent Security Scanner.
Sources
thehackernews.com: https://thehackernews.com/2026/08/amazon-kiro-prompt-injection-can.html
Summary and analysis written by RealGround from the source above; last updated 2026-10-17.