SAFETY

–

02 December 2025 22h16

BrowseSafe and BrowseSafe-Bench are fully open-source. Any developer building autonomous agents can immediately harden their systems against prompt injection. Read more:

BrowseSafe Fine-Tuned Model Outperforms Safety Classifiers

By

–

02 December 2025 22h16

Our findings show that our fine-tuned BrowseSafe model outperforms both off‑the‑shelf safety classifiers and frontier LLMs used as detectors. These gains are possible through fine-tuning on BrowseSafe-Bench data, allowing us to bypass the reasoning latency of larger models.

BrowseSafe: Detection Model Against Prompt Injection Attacks

By

–

02 December 2025 22h16

BrowseSafe is a specialized detection model to defend against evolving prompt injection attacks. It is designed specifically to spot and block malicious instructions hidden in web pages before they can impact AI browser agents.

BrowseSafe-Bench: Security Benchmark for AI Browser Agents

By

–

02 December 2025 22h16

BrowseSafe-Bench is our security benchmark designed to evaluate the robustness of AI browser agents against prompt injection attacks embedded in realistic HTML environments.

BrowseSafe: Open-Source Model Prevents Malicious Prompt Injections

By

–

02 December 2025 22h16

Today we're releasing BrowseSafe and BrowseSafe-Bench: an open-source detection model and benchmark to catch and prevent malicious prompt-injection instructions in real-time.

Prompt Injection Attacks: Hidden Malicious Instructions for AI Agents

By

–

02 December 2025 22h16

Prompt injection involves embedding malicious instructions in text read by AI agents, altering its behavior unnoticed. Attackers hide this in comments, templates, footers, or invisible HTML elements parsed by agents but unseen by users.