CERT-In calls for testing AI agents for unauthorised tool use, privilege abuse

T1Covered by 1 source · first reported by The Hindu — Technology / BusinessLine — Info-tech at 05 Nov, 06:14 UTC

Guidelines require checks on agents’ permissions, task delegation and emergency-stop mechanisms; multi-agent systems must maintain authenticated, logged communications and records of actions

india

Sources

• T1CERT-In calls for testing AI agents for unauthorised tool use, privilege abuseThe Hindu — Technology / BusinessLine — Info-tech05 Nov, 06:14