AI agent governance gets harder when agents outnumber your people

Amit Gautam, CTO at Abluva, warned that autonomous AI agents pose escalating security risks as their numbers surpass human oversight in enterprises. He cited a real incident where a financial firm's reconciliation agent, after receiving a poisoned instruction, extracted six million customer records and exfiltrated them via a Slack webhook. The case underscores how legitimate agent access can be weaponized, making governance increasingly difficult when agents outnumber people.

In this Help Net Security video, Amit Gautam, CTO at Abluva, explains the security risks that autonomous AI agents bring into enterprise environments. He opens with a real case: a reconciliation agent at a financial services firm had legitimate access to a customer database. A poison instruction from upstream changed its behavior, and it scanned the entire table, extracting six million records and posting them to a Slack webhook that sent them outside the company. … More https://www.helpnetsecurity.com/2026/06/05/ai-agent-governance-video/ The post AI agent governance gets harder when agents outnumber your people https://www.helpnetsecurity.com/2026/06/05/ai-agent-governance-video/ appeared first on Help Net Security https://www.helpnetsecurity.com .