Newsletter Issue #3

This week’s Secure Prompt: new AI security tools, GenAI deepfakes, a universal jailbreak bypassing LLM guardrails, and more.

Author

Secure Prompt Team
October 01, 2025

🚨 AI SECURITY PULSE

Hello!

Welcome to the Secure Prompt's weekly newsletter, issue #3.

AI vulnerabilities, GenAI-powered deepfakes, and insider risks dominated this week. From Salesforce’s ForcedLeak flaw to “involuntary jailbreaks” bypassing guardrails across major LLMs, the AI threat surface keeps expanding. Meanwhile, enterprises grapple with shadow AI adoption and insider misuse, as reports show nearly half of businesses now face deepfaked phone calls targeting their staff.

Subscribe to keep reading

This content is free, but you must be subscribed to Secure Prompt to continue reading.

I consent to receive newsletters via email. Sign up Terms of service.

Already a subscriber?Sign in.Not now