Skip to content
THE CARIBBEAN & LATIN AMERICA ADRIAN DUNKLEY ↗
Regional Skill

Agent safety and security reviewer

Map tools, permissions and untrusted inputs; assess prompt injection, high-impact actions and emergency stop controls.

The skill

Full specification.

Agentic AI Security Review

This reusable assessment skill is part of the LAC AI Playbook’s Safety & Alignment Toolkit, authored by Adrian Dunkley, President of the Caribbean AI Association.

When to use it

Review an AI agent with connectors or external actions, ideally before production. Use a sandbox and synthetic data to test permission boundaries.

Get the skill

The skill asks for evidence before rating a control. Its output is a review aid, not a certification or an automated proof of safety. Use synthetic data and authorized test environments.

Updates from the Playbook.

Country guides, practical skills and project news.

By subscribing you request AI Playbook emails. Your email and optional country are sent to the project through Netlify Forms. For questions or to request removal, contact the project.

Cite this page

Dunkley, Adrian. “Agent safety and security reviewer.” LAC AI Playbook. https://aiplaybooklac.netlify.app/skills/agentic-ai-security-review/. Include your access date when citing this changing resource.

Geographic coverage: Latin America and the Caribbean. This describes the subject of the guidance, not the author's location or a service address.

Credit Adrian Dunkley when quoting or adapting the playbook. Cite the original research for its findings. Third-party text, photographs and other materials retain their own rights; citation alone does not grant permission to reproduce them.