BrowseSafe

Vulnerability in Perplexity’s BrowseSafe shows why single models can’t stop prompt injection – TechTalks

vm_adminJanuary 20, 2026

By Ben Dickson Publication Date: 2026-01-19 18:28:00 Lasso Security has discovered significant prompt injection vulnerabilities in BrowseSafe, a new open-source…

Prompt injection in Perplexity BrowseSafe model highlights threats of single-model protection systems

vm_adminJanuary 20, 2026

By Ben Dickson Publication Date: 2026-01-20 15:19:00 Lasso Security has discovered significant vulnerabilities in BrowseSafe, a new open-source tool from…

Perplexity’s BrowseSafe tries to patch the gaping security holes inherent in AI browser agents

vm_adminDecember 7, 2025

By Jonathan Kemper Publication Date: 2025-12-07 09:23:00 Summary Perplexity has developed a security system designed to protect AI browser agents…