PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

Agentic Browser Security: 2025 Year-End Review

wiz.io | blog | #ai-security | #prompt-injection | #web-security | #phishing | #agentic-browser | #ai-browser
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

2025 in review for agentic browsers: zero-interaction exfiltration via ChatGPT Operator, Scamlexity phishing tests, the Gemini Trifecta, plus an autonomy-vs-access matrix for judging AI browser risk.
Published
Collected

Related coverage

blog · vercel.com
The three types of AI bot traffic and how to handle them
Bots account for over 20% of all web traffic. A quarter of that is AI crawlers alone. But not all bots are bad. Some are key to how your site gets discovered. Learn how AI bots shape visibility and what happens if you block them.
research · vercel.com
DeepsecBench: evaluating model performance in finding cybersecurity vulnerabilities
Today we're releasing DeepsecBench, a benchmark that evaluates how well different models find security vulnerabilities in application code.
research · vercel.com
Security boundaries in agentic architectures
A framework for drawing security boundaries in agentic architectures. Most agents run with zero isolation between the agent and the code it generates. Learn where to draw the boundaries, from secret injection to full application sandboxing.
blog · wiz.io
“Black October” for AI Developer Platforms
A series of agentic attacks on AI Developer Platforms has been leading to LLMJacking at scale.
blog · wiz.io
Key Takeaways: AI Threat Readiness Survey Report 2026
Read the AI Threat Readiness Report 2026. Benchmark findings across 100 IT leaders on autonomous agent sprawl, identity risks, and modern cloud governance.
blog · wiz.io
The Rise of Agentic Attacks: What They Look Like, and Where They're Headed
AI agents are changing how attackers operate. Explore real-world cases of agentic attacks, learn how to identify their fingerprints, and discover what they mean for the future of cybersecurity.
Back