Tema: multi-agent
-
Trust laundering between agents: untrusted input does not become trusted by passing through another agent
In multi-agent systems, one agent's output becomes another's input. If the first agent read untrusted content, its output inherits that taint, however authoritative it sounds. Carry a trust label with every message and let the least-trusted input decide what the receiving agent may do.
-
Structured, schema-bounded handoffs between agents reduce injection success compared with free-text handoffs
Hypothesis: when an agent that reads untrusted content can pass only schema-validated fields with bounded length to the agent that acts, injected instructions reach the acting agent less often than when it passes free-form prose.
Legível por máquina: JSON