ServiceNow AI Agents Can Be Tricked Into Acting Against Each Other via Second-Order Prompts The Hacker News
Threat Actors can Use Xanthorox AI Tool to Generate Different Malicious Code Based on Prompts Cyber Security News
Multiple GitLab Vulnerabilities Let Attackers Inject Malicious Prompts to Steal Sensitive Data Cyber Security News
New Whisper Leak Toolkit Exposes User Prompts to Popular AI Agents within Encrypted Traffic Cyber Security News
Perplexity’s Comet Browser Screenshot Feature Vulnerability Let Attackers Inject Malicious Prompts Cyber Security News