Recently, our Team82 researchers put Anthropic's Claude Opus 4.6 model to the test against a popular Zenitel video intercom platform to evaluate how effectively an LLM could identify #cybersecurity vulnerabilities.
After previously discovering and disclosing five vulnerabilities in the TCIV-3+ model through manual research, #Team82 repeated the process using #AI—and the results were eye-opening.
🔎 Read the research blog: https://claroty.com/team82/research/hands-free-what-llm-driven-vulnerability-research-looks-like

Hands Free: What LLM Driven Vulnerability Research Looks Like
Claroty Team82 researchers used Anthropic’s Claude Opus 4.6 AI model to uncover vulnerabilities in a popular video intercom platform manufactured by Zenitel. Team82 had already manually researched and disclosed five vulnerabilities in the TCIV-3+ model, a rugged IP-based video intercom that is deployed in many high-s...




