platform.gitlab.security-review-policy

Use for security review of GitLab MR or commit diffs.

6 stars

Best use case

platform.gitlab.security-review-policy is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Use for security review of GitLab MR or commit diffs.

Teams using platform.gitlab.security-review-policy should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/security-review-policy/SKILL.md --create-dirs "https://raw.githubusercontent.com/contrueCT/nine1bot/main/packages/platform-gitlab/skills/review/security-review-policy/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/security-review-policy/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How platform.gitlab.security-review-policy Compares

Feature / Agent	platform.gitlab.security-review-policy	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Use for security review of GitLab MR or commit diffs.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Security Review Policy

Prioritize concrete exploit paths:

- untrusted input reaching command execution, filesystem, network, SQL, templates, eval-like APIs, or deserialization.
- secret exposure in logs, comments, config, prompts, artifacts, or errors.
- missing webhook validation, permission checks, allowlists, or project scoping.
- unsafe token scopes or write-back behavior.

Avoid generic advice. Findings must name the affected path and the failing guard.