Automatic Tool Invocation when Browsing with ChatGPT - Threats and Mitigations · Embrace The Red - discu.eu

Linking pages

GitHub Copilot Chat: From Prompt Injection to Data Exfiltration · Embrace The Red https://embracethered.com/blog/posts/2024/github-copilot-chat-prompt-injection-data-exfiltration/ 8 comments

Linked pages

The Dual LLM pattern for building AI assistants that can resist prompt injection https://simonwillison.net/2023/Apr/25/dual-llm-pattern/ 116 comments
ChatGPT: Hacking Memories with Prompt Injection · Embrace The Red https://embracethered.com/blog/posts/2024/chatgpt-hacking-memories/ 0 comments

Related searches:

Search whole site: site:embracethered.com

Search title: Automatic Tool Invocation when Browsing with ChatGPT - Threats and Mitigations · Embrace The Red

See how to search.

Submit link to: