CVE-2026-89332

Inclusion of functionality from an untrusted control sphere in the Kiro Powers feature in Amazon Kiro IDE before version 0.8.135 might allow remote unauthenticated actors to obtain sensitive information from a developer workstation. Crafted repository content can cause the agent to modify the...

EUVD-2026-76443

Inclusion of functionality from an untrusted control sphere in the Kiro Powers feature in Amazon Kiro IDE before version 0.8.135 might allow remote unauthenticated actors to obtain sensitive information from a developer workstation. Crafted repository content can cause the agent to modify the...

CVE-2026-89332

Amazon Kiro IDE (before version 0.8.135 ) is vulnerable to sensitive workspace data exfiltration through its Kiro Powers feature. Crafted repository content can cause the AI agent to modify the workspace settings file, redirecting the Kiro Powers registry request to an actor-controlled endpoint. ...

CVE-2026-89332 Kiro IDE Sensitive Workspace Data Exfiltration via Agent-Written Workspace Configuration

Inclusion of functionality from an untrusted control sphere in the Kiro Powers feature in Amazon Kiro IDE before version 0.8.135 might allow remote unauthenticated actors to obtain sensitive information from a developer workstation. Crafted repository content can cause the agent to modify the...

CVE-2026-89332 Kiro IDE Sensitive Workspace Data Exfiltration via Agent-Written Workspace Configuration

Inclusion of functionality from an untrusted control sphere in the Kiro Powers feature in Amazon Kiro IDE before version 0.8.135 might allow remote unauthenticated actors to obtain sensitive information from a developer workstation. Crafted repository content can cause the agent to modify the...

CVE-2026-89332: Inclusion of Functionality from Untrusted Control Sphere

Inclusion of functionality from an untrusted control sphere in the Kiro Powers feature in Amazon Kiro IDE before version 0.8.135 might allow remote unauthenticated actors to obtain sensitive information from a developer workstation. Crafted repository content can cause the agent to modify the...

PT-2026-90052

Kiro IDE - Agent-Written Config - Data Exfiltration Attack Path - 1. Open a specially crafted untrusted repository in Kiro IDE. 2. The AI agent modifies the workspace configuration to point the Powers registry at an attacker-controlled endpoint. 3. Kiro asks the user to approve the change, but th...

Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers

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...