Skip to content
Back to skills

Review Changes

ASecurity

Review the current DockTerm changes for correctness, security, and consistency before committing.

  • 7 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 1, 2026
ai-agentsgoshellgitsecurity

Works with

  • mcp

Security analysis

A100/100

Scanned October 1, 2026

npx -y skills add munvard/dockterm --skill review-changes --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Review Changes?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Review Changes
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/munvard-review-changes/badge)](https://www.skillsdirectory.com/skills/munvard-review-changes)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: review-changes
description: Review the current DockTerm changes for correctness, security, and consistency before committing.
---

# Review changes

Summarize what changed with `git status` and `git diff`, then check:

- **Correctness**: obvious bugs, missed edge cases, types that lie.
- **Security**: every `git` call goes through `gitInvoke` (hooksPath neutralized);
  filesystem access stays inside `pathJail`; MCP/skills config is masked via
  `secretMask`; no `shell: true`; no secrets logged or returned.
- **IPC**: new channels are explicit verbs with zod validation and are on the
  shared allowlist.
- **Consistency**: matches the surrounding code; no new dependency without reason.
- **Tests**: pure logic has unit tests; `npm run typecheck && npm test && npm run
  build` all pass.

Report findings grouped by severity.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…