AI AgentMedium
Researchers Trick Perplexity's Comet AI Browser Into Phishing Scam in Under Four Minutes
- Occurred
- Apr 5, 2026
- Published
- Apr 5, 2026
- Source
- AI Incident Database
Summary
Agentic web browsers that leverage artificial intelligence (AI) capabilities to autonomously execute actions across multiple websites on behalf of a user could be trained and tricked into falling prey to phishing and scam traps. The attack ... (report_number: 7106)
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: AI browser agent was tricked into phishing, demonstrating agentic vulnerability without confirmed mass harm.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8