An AI pentesting agent with credentials and broad access is itself an attack surface, says Terra OffSec CEO

TechNadu · x · 2026-09-22

Shahar Peled, CEO of Terra OffSec, argues that an AI pentesting agent holding credentials, security tools, and broad internal access is itself an attack surface — compromise or misuse could cause disruptive, even irreversible damage.

He calls for human oversight at the decision point for potentially disruptive or irreversible actions: agents can autonomously handle recon, but high-risk moves need a human in the loop.

Related event: AI Pentest Agents With Credentials Are Themselves an Attack Surface(2 posts)→

Original post →

More from coding & agent

coding & agent channel →