AI Security
Protecting AI systems from threats, vulnerabilities, and adversarial attacks
Hero Post
By Adesh Gairola
Claude Tag: an agent that acts as itself, not on your behalf
Claude Tag puts @Claude in Slack as its own per-channel service account, not on behalf of the person who asked. That breaks the delegation model everyone converged on, where the audit log can still name a human. Useful, but it revives the old service-account problems with an AI on top.
Featured Posts
By Adesh Gairola
Kill the God Agent: how we think about agent security
A God Agent is one model wired to every tool on one shared identity, holding the whole lethal trifecta at once: it reads untrusted content, touches private data, and talks to the outside world. You can't filter prompt injection out of that, so you change the architecture instead. Three deterministic moves: scope every agent, sign every call, stop every breach. Break even one leg of the trifecta and the blast radius shrinks.
By Adesh Gairola
Agent identity isn't solved. Here's the model I use anyway.
Agent identity makes more sense as four stacked layers: a tamper-proof token format, cryptographic proof of which workload is running, a delegation chain that keeps the human as the subject, and a way to onboard to a service an agent has never met. Climb all four and you've proven who the agent is. You still haven't proven that what it did was okay.
By Adesh Gairola
Alignment is a Security Problem, Not an Ethics Problem
Misalignment maps onto vulnerability classes security engineers already operate on: backdoors, defense evasion, privilege escalation, exfiltration. Calling it ethics keeps it off security teams' desks. Reframing it as security decides who owns the work, which budget pays, and which playbook applies.
