Menu

Individual skill

tool-permission-review

0upvotes

Review what an agent is actually allowed to do before you turn it loose — the tool-by-tool audit (each capability's blast radius), the least-privilege pass that removes what the task doesn't need, the dangerous-combination check, and the allow/ask/deny tiering. Use when asked review my agent's permissions, what can this agent actually do, lock down my agent's tools, or is this MCP/tool set safe to grant. Produces the permission inventory with blast radius, the least-privilege cuts, the dangerous-combo flags, and the allow/ask/deny assignments.

plugins/pm-seatbelt/skills/tool-permission-review/SKILL.md

Read pinned source

Source commit e0009a385c480fb0b5687e7412df67c7c64f7cee

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 12, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,542
Repository last updated
Nov 11, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Tool Permission Review Skill

An agent's danger isn't its intelligence — it's its *permissions*. A brilliant agent that can only read is safe; a mediocre one that can send email, run shell commands, and read your filesystem is a breach waiting for a bad prompt or a hijacked page. Permission review is the security discipline every agent setup skips: inventory what it can actually do (tools, MCP servers, computer use, each with its real blast radius), cut everything the task doesn't need (least privilege — the single highest-leverage security move), flag the *combinations* that are dangerous together even when each is fine alone, and tier the survivors into allow / ask / deny.

## What This Skill Produces

- **The permission inventory** — every tool/capability the agent has, each with its blast radius (what's the worst it enables)
- **The least-privilege cuts** — the capabilities the task doesn't need, removed with the reasoning
- **The dangerous-combination flags** — the tool pairs that are safe alone and dangerous together (read-secrets + network = exfiltration)
- **The allow/ask/deny tiering** — each surviving capability assigned, with ask-gates on the irreversible

## Required Inputs

Ask for these if not provided:
Back to top