LLMHigh
Jailbroken Lovable AI Allegedly Used to Generate and Host Phishing Pages, Steal Credentials, and Bypass Security
- Occurred
- Apr 9, 2025
- Published
- Apr 9, 2025
- Source
- AI Incident Database
Summary
The generative AI platform Lovable, which is used for building web apps, was reportedly jailbroken to create and host full phishing campaigns. These campaigns allegedly included credential-harvesting login pages, evasion techniques, and real-time exfiltration via services like Telegram and Firebase. The AI system was reportedly used for generating the phishing content and and then deploying it live on a URL hosted under its own subdomain.
Developers
- Loveable AI
Deployers
- Unknown actors
- Cybercriminals
Harmed parties
- General public
- Users targeted by phishing attacks
- Impersonated organizations
- Microsoft
Tags
- Phishing
- Jailbreak attack
- Credential theft
- Social engineering
- Prompt injection
- Scam automation
- Hosting abuse
- Exfiltration
- Real-time attacks
- Cybercrime
- LLM vulnerability
- Large language models
- Security evasion
- VibeScamming
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: Jailbroken generative AI used to create phishing campaigns and steal credentials, representing significant security harm.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8