Access review

Skill maxwellokumu/okaudit-claude-skills/identity-access/access-review

Claude-ready IT audit skills for identity, compliance, appsec, privacy, network, logging, vendor risk, and audit leadership workflows

Install

npx -y skills add maxwellokumu/okaudit-claude-skills --skill access-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Analyse IAM policies for excessive permissions, wildcards, admin-equivalent actions, missing conditions, and inline policies. Use this skill for access review and least-privilege analysis.

SKILL.md

1.7 KB, as published. Nobody here has run it

Access Review

Use this skill when the user asks for IAM review, access review, policy review, excessive permissions analysis, wildcard permission review, or least-privilege checks.

Goal

Analyse IAM policy data to identify dangerous permissions, wildcards, admin-equivalent actions, and missing security conditions.

Workflow

Confirm whether the user is supplying local policy data or wants a cloud-backed mode.
Gather the policy input and any mode selection.
Review README.md if you need exact input formats, supported modes, or sample outputs.
Run main.py with the relevant input, mode, and optional dry-run settings.
Summarize the most dangerous findings first and include remediation guidance.

Inputs

input (string, optional): Path to IAM policy JSON or raw JSON string for local mode.
mode (string, optional): Execution mode: local, aws, or azure.
dry_run (boolean, optional): Use bundled sample data instead of live API calls.

Bundled Files

main.py: executable logic for the skill.
README.md: detailed usage, input expectations, and sample outputs.
sample_input: bundled example IAM policy inputs.
skill.yaml: existing repo manifest retained for this project's original packaging.

Guidance

Prefer local or dry-run analysis before live cloud access when possible.
Prioritize wildcard actions, broad resource scope, and missing MFA or condition constraints.
Clearly separate observed permissions from inferred risk.