Prompt injection isn't the bug, AI agent frameworks are - The Register
... AI apps runs on,” Tal told us. “And the agent needs no dangerous tools to be turned against you: reading the wrong document is enough. We're ...
Read the original at The Register ↗
- Topics
- AI Safety & Existential RiskAI Agents & AutomationCybersecurityGovernance & Risk Management
- Tracked via
- “dangerous AI”