Image created with gemini-2.5-flash-image with claude-sonnet-4-5. Image prompt: Minimalist architectural photograph of an open bank vault door in empty white marble room, elaborate chrome security mechanisms visible, vault interior completely empty, single beam of cold moonlight from high window, dramatic shadows, pristine and untouched, with bold white sans-serif text ‘SECURITY’ overlaid across the composition
BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents https://research.perplexity.ai/articles/browsesafe
Building Safer AI Browsers with BrowseSafe https://www.perplexity.ai/hub/blog/building-safer-ai-browsers-with-browsesafe
New on our Frontier Red Team blog: We tested whether AIs can exploit blockchain smart contracts. In simulated testing, AI agents found $4.6M in exploits. The research (with @MATSprogram and the Anthropic Fellows program) also developed a new benchmark: https://x.com/AnthropicAI/status/1995631802032287779
Leave a Reply