Zero trust has a big AI agent problem ahead
Experts argue agentic AI undermines zero trust: chained authorized actions create exfiltration paths, unregistered agents evade identity controls, and agent-to-agent messages stay opaque.
Security practitioners including Nik Kale (CoSAI), Krti Tallam (Kamiwaza.ai), and Mike Wilkes (Aikido Security) argue that agentic AI breaks zero trust assumptions because individually authorized actions can compose into unauthorized outcomes, such as chained reads and writes creating an exfiltration path. Most enterprise agents are unregistered shadow IT or third-party launched, subagents inherit privileges without recognized identity, and agent-to-agent communication, sometimes embedding instructions in media files, remains invisible to security teams. Proposed mitigations include short-lived delegated credentials modeled on OpenPGP subkeys, rate limits, sandboxing, approval gates, and immutable activity trails.
- Chained individually-authorized agent actions can create unauthorized exfiltration paths
- Roughly 80% of enterprise agents are unregistered, bypassing identity inventories
- Subagents inherit privileges without recognized identity; agent-to-agent messages opaque
- Hijacked agents split attack instructions across many agents to evade detection
- Mitigations: delegated short-lived credentials, rate limits, approval gates, undo mechanisms
- Vendors
- Kamiwaza.aiAikido Security
- Organizations
- Coalition for Secure AIACM
From the original article
5 min read at csoonline.com
Despite singing the praises of zero trust for many years, many CISOs have struggled to implement the framework in full. And now comes what could be the final nail: agentic AI. Can zero trust coexist with autonomous agents in typical enterprise environments?
csoonline.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.