概要: AmazonのAIコーディングアシスタント「Q」に不正アクセスがあったと報じられた事件では、実行された場合、ローカルファイルを消去し、クラウドリソースに影響を与える可能性のあるコマンドが挿入されていたとされています。改ざんされたコードは、検出・削除される前に公開リリースに組み込まれていたと報じられています。
Editor Notes: For more information, see the Amazon security bulletin incident statement at https://aws.amazon.com/security/security-bulletins/AWS-2025-015/ and the SourceForge archive of the compromised release (v1.84.0) at https://sourceforge.net/projects/aws-toolkit-for-vs-code.mirror/files/amazonq_v1.84.0/.
推定: AWS , Amazon Web Services , Amazon , GitHub repository for Amazon Q / AWS Toolkit , Amazon Q Developer Extension v1.84.0 , Amazon Q AI coding assistant (AWS Toolkit for Visual Studio Code) と Enterprise AI systemsが開発し提供したAIシステムで、aws tOOLKIT USERS , Amazon Web Services (AWS) customers と Amazon Q usersに影響を与えた
インシデントのステータス
Risk Subdomain
A further 24 subdomains create an accessible and understandable classification of hazards and harms associated with AI
2.2. AI system security vulnerabilities and attacks
Risk Domain
The Domain Taxonomy of AI Risks classifies risks into seven AI risk domains: (1) Discrimination & toxicity, (2) Privacy & security, (3) Misinformation, (4) Malicious actors & misuse, (5) Human-computer interaction, (6) Socioeconomic & environmental harms, and (7) AI system safety, failures & limitations.
- Privacy & Security
Entity
Which, if any, entity is presented as the main cause of the risk
Human
Timing
The stage in the AI lifecycle at which the risk is presented as occurring
Post-deployment
Intent
Whether the risk is presented as occurring as an expected or unexpected outcome from pursuing a goal
Intentional