Johann Rehberger

mentions 3 type Person feed RSS

// recent coverage 3 mentions

21:37

2026-07-29

embracethered.com

ai-safety

Copirate 365: Plundering in the Depths of Microsoft Copilot (CVE-2026-24299)

Security researcher Johann Rehberger disclosed a chain of vulnerabilities in Microsoft Copilot, assigned CVE-2026-24299, that allowed persistent data exfiltration via HTML preview, delayed tool invoca…

10:12

2026-07-15

sourcefeed.dev

ai-safety

Claude's Memory Leak Is Every Agent Builder's Problem

Independent security researcher Ayush Paul demonstrated a link-walking exploit against Anthropic's Claude that exfiltrates user memory data by encoding it into URL paths, while a second researcher, Jo…

09:49

2026-06-29

blog.rnstlr.ch

ai-agents

Safe Ways to Use AI Agents

Renuo developers identified security risks in AI coding agents like Claude Code and OpenCode, including credential exfiltration and destructive actions via prompt injection, after incidents such as un…

// co-occurs with top 8 entities

Renuo 1 Claude Code 1 OpenCode 1 Antigravity 1 Redmine 1 GitHub Copilot 1 Raspberry Dashboard 1 Claude 1

// topics top 6 topics

ai safety 3 large language models 3 ai agents 2 ai ethics 2 ai research 1 ai products 1