Keeping your data safe when an AI agent clicks a link

kept by eddie jan 29

OpenAI prevents URL-based data exfiltration by only allowing AI agents to auto-fetch URLs that were independently observed in a public web index.

Designing AI agents to resist prompt injection
OpenAI argues that defending against prompt injection in AI agents requires treating attacks as social engineering and designing systems to constrain impact rather than just filtering inputs.
also on #prompt-injection, ChatGPT, #security, #ai-agents
Security boundaries in agentic architectures - Vercel
Vercel recommends separating agent harness from generated code execution in isolated sandboxes with secret injection to prevent prompt injection and credential theft in agentic architectures.
also on #prompt-injection, #security, #ai-agents