ended6월 29일· 1 sources

Want AI Agents That Don't Spill Secrets? Don't Give Them Secrets

Why it matters

Some time ago, I reviewed an AI agent implementation and found an API key in the system prompt. The developer didn't realize it, but the LLM did. LLMs cannot natively separate instructions from data. ...

1
Sources
+0
24h
Growth
84d
Active

Sources

Related Issues