Skip to content
MoorAI
06 — defence & response

Permission right-sizing

Cutting the permissions an agent is granted down to the ones it uses: comparing what a configuration allows — tools, commands, directories, MCP servers, auto-approval settings — with a record of what was actually called, then removing whatever was never needed or moving it behind a prompt. It is least privilege made measurable, and it has to be repeated, because grants and usage both drift.

How MoorAI handles it: MoorAI's opt-in allow trail sends one content-free record per allowed tool call (the tool name, never its arguments), which is the usage half of the comparison.

Related terms

  • Least privilege for AI agents Defence & response

    The principle that an agent gets only the tools, files, network destinations and credentials its task needs, for only as long as it needs them.

  • Excessive agency Attack concepts

    The OWASP Top 10 for LLM Applications entry (LLM06:2025) for a system that can be made to take damaging actions in response to unexpected, ambiguous or…

Defence & response

The vocabulary of running controls for agents: knowing what AI is present, cutting what it may do down to what it uses, catching misuse, and reconstructing an incident afterwards. Where MoorAI implements a term, a separate line under the definition says how; the definition itself stays vendor-neutral. To check one agent's configuration against these ideas, use the free permission right-sizer.

Permission right-sizing is term 6 of 10 in this part of the glossary.

Get started free Full glossary → How we test → Community agent on GitHub ↗

This page is one entry from the agentic AI security glossary, which defines 82 terms in the same style. Where a term belongs to a published taxonomy or standard — the HackAgent attack families, the OWASP lists, AMTSO's guidelines, MITRE ATLAS, ISO/IEC 42001, the NIST AI RMF, the EU AI Act, W3C Trace Context, the MCP specification — the authoritative wording is the source document's, not ours, and specifics should be verified there. "Lethal trifecta" is Simon Willison's term. OWASP® is a trademark of the OWASP Foundation; ATT&CK® and ATLAS™ are trademarks of The MITRE Corporation. Naming a framework here is description, not a claim of certification or endorsement.