Glossary

AI Agent

An autonomous system using an LLM to make decisions, call tools, and execute tasks without direct human intervention. AI agents introduce specific risks: uncontrolled code execution, excessive data access, and manipulation via prompt injection. Their attack surface is proportional to the number of tools they can access.

Related Pages

ai agents function calling attack surface→mcp→

Other Terms

2FA/MFA (Multi-Factor Authentication)

Account Takeover (ATO)

ADCS (Active Directory Certificate Services)

AES (Advanced Encryption Standard)

← Back to glossary

Want to know what your AI agent can do?

Tell us about your agent, its tools, and client context. We will come back with the right review scope.

Discuss your audit