Review a proposed or implemented change for security boundary violations, unsafe data handling, auth flaws, secret exposure, injection, and abuse risk.
Scanned 9/11/2026
Install to Claude Code
npx -y skills add Dadmin88/hermes-profile-packs --skill security-review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Security Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/dadmin88-security-review)More formats (shields.io, HTML) on the badges page.
---
name: security-review
description: Review a proposed or implemented change for security boundary violations, unsafe data handling, auth flaws, secret exposure, injection, and abuse risk.
---
# Security Review
Use for changes that affect authentication, authorization, sensitive data, external input, execution, networking, secrets, or trust boundaries.
## Procedure
1. Establish assets, actors, privileges, data sensitivity, and trust boundaries affected by the change.
2. Trace untrusted input and authority decisions through the implementation.
3. Review authentication, authorization, tenant isolation, validation/encoding, secret handling, cryptographic use, logging, dependencies, and failure behavior as relevant.
4. Look for confused-deputy behavior, privilege escalation, unsafe defaults, bypass paths, and information leakage.
5. Rank findings by realistic exploitability and impact.
6. Provide concrete remediation and validation steps.
## Quality gate
Every blocking security finding should identify the violated boundary or control and a plausible impact. Avoid generic hardening advice disconnected from the change.Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling