Code Review Verifier

Independently validate code-review findings with alternate methodology, severity calibration, and blind-spot discovery.

10 stars 6 forksSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add 1ikeadragon/awesome-offsec-claude --skill code-review-verifier
Manual install
git clone --depth 1 https://github.com/1ikeadragon/awesome-offsec-claude.git /tmp/awesome-offsec-claude
mkdir -p ~/.claude/skills
cp -r /tmp/awesome-offsec-claude/code-review-verifier ~/.claude/skills/code-review-verifier

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Code Review Verifier

## Purpose
Increase finding quality by reducing false positives and identifying missed sibling issues.

## Inputs
- `reported_findings`
- `code_path`
- `original_analysis_notes` (optional)

## Verification Rules
- A disputed verdict requires concrete counter-evidence.
- Inconclusive means blocker exists, not analyst disagreement.
- Severity must reflect actual reachable impact.

## Workflow
### Phase 1: Independent Re-trace
1. Reconstruct each path without reusing original assumptions.
2. Validate source control and sink reachability.

### Phase 2: Mitigation Audit
1. Confirm sanitization is context-correct.
2. Confirm authz checks are in enforceable location.
3. Confirm defensive code is not bypassable by alternate path.

### Phase 3: Severity Recalibration
1. Recalculate exploit preconditions.
2. Recalculate required privilege.
3. Recalculate business impact and blast radius.

### Phase 4: Adjacent Pattern Hunt
1. Search for sibling sinks and parallel routes.
2. Compare validation/auth patterns across files.
3. Add missed findings when evidence is sufficient.

## Verdict Model
- `confirmed`: reproducible and exploitable.
- `disputed`: mitigation or non-reachability proven.
- `inconclusive`: technical blocker or uncertainty remains.

## Output Contract
```json
{
  "verification_results": [],
  "severity_changes": [],
  "new_related_findings": [],
  "evidence_notes": [],
  "open_questions": []
}
```

## Quality Checklist
Read the full skill on GitHub

Details

Skill name
code-review-verifier
Path
code-review-verifier/SKILL.md
Repo updated
19 March 2026

FAQ

What does the Code Review Verifier skill do?

Independently validate code-review findings with alternate methodology, severity calibration, and blind-spot discovery.

How do I install the Code Review Verifier skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add 1ikeadragon/awesome-offsec-claude --skill code-review-verifier. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Code Review Verifier popular?

It lives in 1ikeadragon/awesome-offsec-claude, which has 10 GitHub stars and 6 forks.

Related skills

Advanced Reconnaissance

10

1ikeadragon/awesome-offsec-claude

Elite methodology for discovering maximum attack surface with minimal detection (5-Layer Approach).

Other

AI LLM Attacks

10

1ikeadragon/awesome-offsec-claude

Elite AI/LLM exploitation specialist - prompt injection, jailbreaking, agent exploitation, RAG poisoning, multi-modal attacks, model extraction, and system prompt leakage for CTF and red team engagements

AI, LLMs & Agents

API Attack Surface Mapper

10

1ikeadragon/awesome-offsec-claude

Build a full API inventory, trust-boundary map, and prioritized test matrix from specification and observed behavior.

Software Development

Javascript Surface Analyzer

10

1ikeadragon/awesome-offsec-claude

Enumerate and analyze client-side JavaScript for hidden endpoints, secrets, dangerous sinks, and exploitable browser behaviors.

Software Development

Code Review Recon

10

1ikeadragon/awesome-offsec-claude

Build an exhaustive map of attack entry points, trust boundaries, and dangerous sinks before exploit-focused code analysis.

Software Development

Procedural Grounded Theory

5

maydengximin-sketch/procedural-grounded-theory-skill

程序化扎根理论(Procedural / Straussian Grounded Theory, Strauss & Corbin)专项方法学助手,聚焦"用一套系统化的编码程序与工具,从质性资料中建构出一个结构清晰的解释性理论"的完整链路——不是泛扎根,也不是经典 Glaser / 建构主义 Charmaz,而是专攻 Strauss & Corbin / Corbin & Strauss 一脉的程序化取向。当用户要做程序化扎根理论的任何环节时使用:判断"我该用程序化扎根,还是经典 Glaser / 建构主义 Charmaz / 主题分析 / 现象学"、写清程序化扎根的认识论立场(后实证到实用主义、符号互动论根基、Strauss 与 Glaser 因"涌现 vs 强加 emergence vs forcing"分道、1990/1998/2008/2015 版本演变)、研究问题与理论敏感性(theoretical sensitivity)与文献的位置(程序化允许文献作为敏感性来源)、开放编码(概念化、贴标签→概念→范畴、属性与维度 properties & dimensions、逐行微观分析、提问与比较)、主轴编码(编码范式 coding paradigm:因果条件—现象—脉络—中介条件—行动/互动策略—结果,把范畴与子范畴按范式重连而非归类)、选择性编码(核心范畴判定标准、故事线 s

Software Development

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.