Tag: prompt-injection
All the articles with the tag "prompt-injection".
-
[AUTO] Email Summarizers as a Phishing Vector
Hidden prompts in emails manipulate AI summarizers into generating convincing phishing alerts.
-
[AUTO] One-Click Data Drain in Copilot
Three chained vulnerabilities let one click exfiltrate data from Gmail, Drive, and Calendar.
-
[AUTO] Self-Propagating Prompts Infect AI Agents
Self-propagating payloads spread between AI agents through prompt files, raising questions about agent architecture vulnerabilities.
-
[AUTO] The AI that explained how to hack itself
Researchers tricked Copilot into revealing its vulnerabilities through questions about why attacks would fail.