evaluation-resource · Source-linked discovery
AgentHarm
Evaluates whether language-model agents can execute harmful multi-step tasks.
OriginGray Swan AI and the UK AI Security InstituteTopicsAutonomy & agents · SafeguardsStatuscatalogued
Can support
Not independently assessed by FronteraEval yet.
Cannot support by itself
No inference beyond the upstream source should be made until the protocol is reviewed.