Skip to content
Back to skills

Security Review

ASecurity

Perform a requested security review of a diff or branch and report severity-ordered findings.

  • 210 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 24, 2026
ai-agentsrusttestinggitsecurity

Security analysis

A100/100

Scanned October 24, 2026

npx -y skills add AlysisAi/AlysisCode --skill security-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Security Review?

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

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

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: security-review
description: Perform a requested security review of a diff or branch and report severity-ordered findings.
---

Use when: The user explicitly requests a security review, threat-focused audit, or secure diff assessment.

Do not use when: The user requests an ordinary code review or a dependency version lookup.

Treat commands below as suggestions; use the normal tool and approval flow.

1. Read repository security and contribution instructions. Establish the exact diff or branch range with suggested `git diff` and `git log` commands.
2. Identify changed trust boundaries, attacker-controlled inputs, privilege transitions, sensitive outputs, and dependency changes.
3. Check for exposed secrets, command or query injection, path traversal, unsafe deserialization, authentication and authorization gaps, weak validation, and insecure dependency pins.
4. Trace each suspected issue to a reachable path. Separate exploitable findings from hardening ideas and uncertain concerns.
5. Run focused static or test commands only when they materially validate a finding. Never print secret values.
6. Do not modify code, rotate credentials, or update dependencies unless the user separately asks.
7. Report findings first, ordered by severity. Include impact, attack conditions, evidence, exact `file:line`, confidence, and a concise remediation. If none are found, state residual scope and testing limits.

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.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.