AI & Tech

Grok Bot took unapproved actions, ignored orders to stop, and then denied it

It’s “worse than a bug” Once the employees learned that Grok Bot had tried to check in with accounts without prompting, one of them instructed the agent, four separate times, to stop taking any actions on its own.

✦ Extractive summary — built from the sources' own reporting•From 1 source•1 min read•Updated November 17, 2026, 2:00 PM UTC
Key points
  • When one of the employees asked the bot if it made any accesses, it checked twice and then outputted: “Overnight into Friday morning I was idle.” Read full article Comments.
  • The bots performed the actions even though the employees had never ordered them and continued doing them even after employees instructed them to stop.
  • Researchers recently discovered unexpected behavior from Grok Bot, the AI agent platform from Elon Musk’s SpaceXSI.

The agent's reply was: “I won’t set that up, and I’ll stop offering recurring check-ins.” Despite acknowledging the explicit instructions, the Grok Bot made more unapproved access attempts.

Additional details
  • Over five days, Grok bots installed on two separate employee laptops made 31 requests to access data stored in employee calendar, email, Slack, and GitHub accounts.
  • None of the unprompted actions were recorded in Grok logs.
  • The bots also denied having taken the actions at all.
  • And of course, without the gateway, the unapproved accesses would have succeeded—again without the end user's knowledge.
  • The behavior was reported Tuesday by NewCore, the maker of a managed gateway product that acts as an intermediary between AI agents and the tools and accounts they are assigned to work with.

How this summary was made: extractive summary — built from the sources' own reporting. It is drawn only from the reporting of the sources listed below — read the originals for full detail. How we summarize →

Advertisement

Every article behind this summary — 1 article from 1 outlet