Tag: ai-security
All the articles with the tag "ai-security".
-
Weekly Roundup: Three sandbox escapes, 974 CVEs, and OpenAI's self-audit
Sandbox escapes in ChatGPT, DeepSeek Harness and Docker; a record Patch Tuesday; and OpenAI publishing six of its own misalignment incidents.
-
[AUTO] Plugin4Shell breaks AI agent supply chains
A zero-click RCE in top AI coding agents exploits a fundamental flaw in how they verify code commits.
-
[AUTO] Spain Reports First Alleged AI-Powered Data Theft
Spain's data protection authority logged its first data breach executed by an autonomous AI agent, though the evidence remains limited.
-
[AUTO] BragJack: One Malicious Extension, Five Browsers
A single browser extension can hijack AI assistants across Chrome, Edge, Opera, and Perplexity by exploiting a shared architectural flaw.