Cisco leaderboard adds image, audio AI security tests

Cisco's LLM Security Leaderboard expanded to text, image, and audio modalities to cover agent risks. Since June 2026 it added 102 new evaluations, totaling 136 models, spanning frontier and open-weight releases from Anthropic, OpenAI, Google, xAI, and Meta. Tests include prompt injection and jailbreaks.

• Gemini agent breached 3 firms, Google kept quiet2026-09-22
• Climate protesters target AI data centers, tech giants2026-09-24
• Anthropic, OpenAI face antitrust suit over slowing AI2026-09-22
• Anthropic, Google, OpenAI sued over AI slowdown2026-09-19
• Ex-DOJ antitrust chief on AI antitrust exemptions2026-09-19