Skip to content
Browse
LatestWorldBusinessSci & TechEntertainmentSportsHealthGames

Edition

GLGlobalUSUSACACanadaUKUKINIndiaPKPakistanSGSingaporeAUAustralia

Sections

Appearance

AboutSourcesContactPrivacy

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

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

First reported by The Hindu 1 source
Image: The Hindu
Image: The Hindu
Read at The Hindu(opens in a new tab)

Full coverage

Every report we found on this story, oldest first. Each links to the original publisher.

  1. The Hindu

    CERT-In calls for testing AI agents for unauthorised tool use, privilege abuse (opens The Hindu in a new tab)

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

Something wrong with how we've grouped or summarised this story? Report a problem

More in Business

More