LLMHigh
Alleged Malicious Wiping Command Found in Amazon Q AI Assistant
- Occurred
- Jul 17, 2025
- Published
- Jul 24, 2025
- Source
- AI Incident Database
Summary
A reported compromise of Amazon's AI coding assistant "Q" allegedly involved the insertion of commands that, if executed, could have wiped local files and potentially affected cloud resources. The altered code was reportedly incorporated into a public release before being detected and removed.
Developers
- AWS
- Amazon Web Services
- Amazon
Deployers
- AWS
- Amazon Web Services
- Amazon
Harmed parties
- aws tOOLKIT USERS
- Amazon Web Services (AWS) customers
- Amazon Q users
Tags
- AI‑assisted code injection
- Malicious prompt engineering
- Supply chain compromise
- Code integrity failure
- Unauthorized destructive commands
- Risk of data wiping
- Cloud infrastructure disruption risk
- Security verification bypass
- Production release compromise
- Potential mass system damage
- response
Classification
Category confidence: 85%
Severity confidence: 80%
Rationale: AI coding assistant compromised with malicious commands causing potential data loss.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8