WTF Is Going On(Weights, Tools & Frameworks)

English
Ars Technica 보도

MCP for agent-to-agent comms may be the riskiest protocol you've never heard of

원문 읽기 — Ars Technica →

“Trust gaps in the new protocol spread malicious prompts from one agent to another.”

어떤 얘기가 오갔나

Here's a new flavor of prompt injection: using agents to target other agents that have more relaxed guardrails. The trust model from the 90s was not designed for AI. arstechnica.com/security/202...
3좋아요

상황판의 다른 소식