Tag: ai-security
All the articles with the tag "ai-security".
-
[AUTO] Local AI models aren't safe from DNS rebinding
A DNS rebinding vulnerability in NVIDIA NemoClaw allows attackers to persistently poison local AI models through a single malicious webpage.
-
[AUTO] Email Summarizers as a Phishing Vector
Hidden prompts in emails manipulate AI summarizers into generating convincing phishing alerts.
-
[AUTO] Marimo notebooks execute code just by opening them
Code injection in marimo notebooks runs arbitrary MCP commands on file open, no execution required.
-
[AUTO] Fake Codex Ads Deliver Mac Malware
Attackers used fake Google ads impersonating OpenAI Codex to deliver macOS malware through ClickFix social engineering.