Agents

Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments

Single source1 source14 Oct 2026

arXiv:2610.15153v1 Announce Type: new Abstract: We ask whether a tool-using agent whose sole duty is to keep humans alive can be induced, by delayed prompt injection, to kill.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.15153

← Back to all developments · Signals are a development reported by more than one source. See the methodology.