Newsletter Issue #8

This week’s Secure Prompt: Copilot Mermaid injection, agent data leaks, MCP hijacking, AI receipt fraud, Claude exfil - and more.

Author

Secure Prompt Team
November 05, 2025

In partnership with

🚨 AI SECURITY PULSE

Hello!

Welcome to Secure Prompt’s weekly newsletter, issue #8.

This week’s spotlight: OpenAI's new AI security tool, AI agents leaking data via “simple” web searches, and MCP prompt hijacking turning helpful tools into backdoors. Expense fraud is spiking with AI-generated receipts, while a new Claude Code Interpreter exfiltration technique shows how allowlisted APIs can become covert data channels. The takeaway: agent permissions, document trust, and browser automation remain the weak links in today’s AI stack.

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