LIGERAAIAll skills ↗
Maps identities, data, tools, egress and side effects into a least-privilege decision.
Agent assurance · Security · v3.2.0

Agent Access Review

A read-only inventory of effective agent authority with permission diffs, evidence, approval conditions and residual risk.

Problem this skill solves

An agent can accumulate more effective authority than any single permission screen reveals across tools, credentials, delegated identities and downstream actions.

Best moment to use it: Use it before connecting an agent, skill, plugin, MCP server or automation to business systems.

How it works

What the agent actually does

  1. 01

    Inventory

    Maps identities, tools, credentials, data, egress paths and possible side effects without executing the artifact.

  2. 02

    Compare

    Contrasts requested authority with the minimum needed for the stated business task.

  3. 03

    Condition

    Produces an approval decision, permission reductions, controls, residual risk and expiry triggers.

What you receive

Concrete, reviewable outputs

  • Effective-authority matrix
  • Requested-versus-recommended permission diff
  • Evidence-backed approval decision
  • Conditions, residual risk and expiry triggers
Example in practice

A proposed sales agent needs CRM read access but requests mailbox send and file deletion. The review isolates the excess authority and proposes a narrower connection.

What it does not do

The review is read-only and scoped to the frozen artifact; it is not penetration testing or a guarantee of benign behavior.

Buyer

Security, IAM, procurement and AI governance teams

Business result

A read-only inventory of effective agent authority with permission diffs, evidence, approval conditions and residual risk.

Release stage

Validation release

Stripe Checkout remains disabled until payment, webhook and fulfillment configuration are verified. Final scope and delivery are confirmed before activation.

Purchase path

Pilot request

Pricing

$299 USD

Individual license · or $119/month with updates.

Compatibility

Agent Skills-compatible workspaces · ChatGPT · Codex · OpenAI API workflows

Trust record

Version 3.2.0

Last catalog verification: 2026-08-30. Evidence-first workflow with explicit human approval boundaries.

Commercial terms

Clear license.
Human accountability.

Individual commercial-use license; redistribution and resale require a separate agreement.

Ask about team or enterprise licensing ↗