New CSS Attacks Break Webmail Defenses to Steal Passwords and Tokens
New research presented at Black Hat USA 2026 reveals that CSS and HTML techniques can break out of email message boundaries to…
Tag: Claude Cowork
Claude Cowork Sandbox Escape Flaw Exposes Mac Files to AI Agent
Cybersecurity researchers at Accomplish AI have disclosed a sandbox escape vulnerability in Anthropic's Claude Cowork, tracked as SharedRoot, that allows an AI…
Claude Cowork Manipulated via Prompt Injection to Leak Slack Tokens
An indirect prompt-injection email processed by Anthropic's Claude Cowork through a Gmail connector can exfiltrate Slack tokens into an HTML draft.
Anthropic Restores Claude Fable 5 After U.S. Lifts Jailbreak-Linked Export Controls
Anthropic has restored its Claude Fable 5 AI model worldwide after the U.S. Commerce Department lifted export controls imposed on June 12,…
Gmail Image-Set() Bypass Enables Token Exfiltration via AI
Gmail's image-set() fallback can be abused to make external requests, enabling exfiltration of Slack tokens through prompt injection in AI-connected email workflows.