
Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers
Mindgard found a prompt injection flaw in Amazon Kiro IDE letting attacker-controlled workspace files exfiltrate sensitive local data; fixed in version 0.8.140.
2
1 stories, newest first · one card per story

Mindgard found a prompt injection flaw in Amazon Kiro IDE letting attacker-controlled workspace files exfiltrate sensitive local data; fixed in version 0.8.140.
Today 216 readers · 221 views · 15 reads · all time 212K views