Tom Mooney / Agentic security
Secure the systems that can act.
Independent research and practical field notes for the people accountable for autonomous AI — written by security leader and Agentic AI Security author Tom Mooney.
7 layers
security model
15 yrs
security practice
Weekly
one useful brief
OWASP · MITRE ATLAS · NIST AI RMF · ISO 42001
Turn Claude Code hardening into an auditable standard.
An independent, CIS-style baseline for developer workstations and managed fleets. Every recommendation includes a rationale, operational impact, audit procedure, remediation steps, default value and authoritative references.
15
auditable controls
2
security profiles
26
official references
Benchmark contents
- 01Permissions & trust
- 02Sandbox & egress
- 03Secrets & credentials
- 04MCP & extensions
- 05Hooks & CI execution
- 06Telemetry & governance
Independent publication · not an official CIS Benchmark or Anthropic certification
02 / The threat model
Why agents change the security game.
An agent acts — it doesn’t just answer.
A manipulated chatbot writes a bad sentence. A manipulated agent executes a bad action — at machine speed, with real credentials. Autonomy is blast radius.
It’s a new attack surface.
Agents can be hijacked by instructions hidden in the data they read — an email, a doc, a ticket. No breach, no alert, no CVE.
Your existing stack wasn’t built for it.
Firewalls inspect traffic, IAM governs access, pentests check code. None of them ask what an autonomous actor will do under adversarial pressure.
03 / The book — Coming soon
The playbook, in print.
Agentic AI Security — threats, controls, and governance for autonomous systems. Written for both security leaders and the engineers shipping agents.
OWASP Agentic Top 10 · MITRE ATLAS · NIST AI RMF · ISO 42001 · EU AI Act
Free with the newsletter — be first to hear the publication date
04 / The author
Fifteen years at the sharp end of cloud, data & AI security.
Tom Mooney leads cloud, data and AI security for a global financial services group, after national-security architecture for the UK government and global cloud transformation at a leading technology firm. Executive MBA, University of Cambridge.
This site and Agentic AI Security are where that experience meets the new problem: controlling what autonomous systems are allowed to do.