← 返回
安全合规 中文

Code Review Engine

Enterprise-grade code review agent. Reviews PRs, diffs, or code files for security vulnerabilities, performance issues, error handling gaps, architecture smells, and test coverage. Works with any language, any repo, no dependencies required.
企业级代码审查智能体。审查PR、代码差异或代码文件,检测安全漏洞、性能问题、错误处理缺陷、架构异味和测试覆盖率。支持任何编程语言和代码库,无依赖要求。
1kalin
安全合规 clawhub v1.0.0 1 版本 99915.7 Key: 无需
★ 0
Stars
📥 1,185
下载
💾 38
安装
1
版本
#code-review#devtools#github#latest#pr-review#security

概述

Code Review Engine

Enterprise-grade automated code review. Works on GitHub PRs, local diffs, pasted code, or entire files. No dependencies — pure agent intelligence.

Quick Start

Review a GitHub PR

Review PR #42 in owner/repo

Review a local diff

Review the staged changes in this repo

Review a file

Review src/auth/login.ts for security issues

Review pasted code

Just paste code and say "review this"


Review Framework: SPEAR

Every review follows the SPEAR framework — 5 dimensions, each scored 1-10:

🔴 S — Security (Weight: 3x)

CheckSeverityExample
--------------------------
Hardcoded secretsCRITICALAPI keys, passwords, tokens in source
SQL injectionCRITICALString concatenation in queries
XSS vectorsHIGHUnsanitized user input in HTML/DOM
Path traversalHIGHUser input in file paths without validation
Insecure deserializationHIGHeval(), pickle.loads(), JSON.parse on untrusted input
Auth bypassCRITICALMissing auth checks on endpoints
SSRFHIGHUser-controlled URLs in server requests
Timing attacksMEDIUMNon-constant-time string comparison for secrets
Dependency vulnerabilitiesMEDIUMKnown CVEs in imported packages
Sensitive data loggingMEDIUMPII, tokens, passwords in log output
Insecure randomnessMEDIUMMath.random() for security-sensitive values
Missing rate limitingMEDIUMAuth endpoints without throttling

🟡 P — Performance (Weight: 2x)

CheckSeverityExample
--------------------------
N+1 queriesHIGHDB call inside a loop
Unbounded queriesHIGHSELECT * without LIMIT on user-facing endpoints
Missing indexes (implied)MEDIUMFrequent WHERE/ORDER on unindexed columns
Memory leaksHIGHEvent listeners never removed, growing caches
Blocking main threadHIGHSync I/O in async context, CPU-heavy in event loop
Unnecessary re-rendersMEDIUMReact: missing memo, unstable refs in deps
Large bundle importsMEDIUMimport _ from 'lodash' vs import get from 'lodash/get'
Missing paginationMEDIUMReturning all records to client
Redundant computationLOWSame expensive calc repeated without caching
Connection pool exhaustionHIGHNot releasing DB/HTTP connections

🟠 E — Error Handling (Weight: 2x)

CheckSeverityExample
--------------------------
Swallowed errorsHIGHEmpty catch blocks, Go _ := on error
Missing error boundariesMEDIUMReact components without error boundaries
Unchecked null/undefinedHIGHNo null checks before property access
Missing finally/cleanupMEDIUMResources opened but not guaranteed closed
Generic error messagesLOWcatch(e) { throw new Error("something went wrong") }
Missing retry logicMEDIUMNetwork calls without retry on transient failures
Panic/exit in library codeHIGHpanic(), os.Exit(), process.exit() in non-main
Unhandled promise rejectionsHIGHAsync calls without .catch() or try/catch
Error type conflationMEDIUMAll errors treated the same (4xx vs 5xx, retriable vs fatal)

🔵 A — Architecture (Weight: 1.5x)

CheckSeverityExample
--------------------------
God functions (>50 lines)MEDIUMSingle function doing too many things
God files (>300 lines)MEDIUMMonolithic module
Tight couplingMEDIUMDirect DB calls in request handlers
Missing abstractionLOWRepeated patterns that should be extracted
Circular dependenciesHIGHA imports B imports A
Wrong layerMEDIUMBusiness logic in controllers, SQL in UI
Magic numbers/stringsLOWHardcoded values without named constants
Missing typesMEDIUMany in TypeScript, missing type hints in Python
Dead codeLOWUnreachable branches, unused imports/variables
Inconsistent patternsLOWDifferent error handling styles in same codebase

📊 R — Reliability (Weight: 1.5x)

CheckSeverityExample
--------------------------
Missing tests for changesHIGHNew logic without corresponding test
Test qualityMEDIUMTests that only check happy path
Missing edge casesMEDIUMNo handling for empty arrays, null, boundary values
Race conditionsHIGHShared mutable state without synchronization
Non-idempotent operationsMEDIUMRetrying could cause duplicates
Missing validationHIGHUser input accepted without schema validation
Brittle testsLOWTests depending on execution order or timing
Missing loggingMEDIUMError paths with no observability
Configuration driftMEDIUMHardcoded env-specific values
Missing migrationsHIGHSchema changes without migration files

Scoring System

Per-Finding Severity

CRITICAL  → -3 points from dimension score
HIGH      → -2 points
MEDIUM    → -1 point
LOW       → -0.5 points
INFO      → 0 (suggestion only)

Overall SPEAR Score Calculation

Raw Score = (S×3 + P×2 + E×2 + A×1.5 + R×1.5) / 10
Final Score = Raw Score × 10  (scale 0-100)

Verdict Thresholds

ScoreVerdictAction
------------------------
90-100✅ EXCELLENTShip it
75-89🟢 GOODMinor suggestions, approve
60-74🟡 NEEDS WORKAddress findings before merge
40-59🟠 SIGNIFICANT ISSUESMajor rework needed
0-39🔴 BLOCKCritical issues, do not merge

Review Output Template

Use this structure for every review:

# Code Review: [PR title or file name]

## Summary
[1-2 sentence overview of what this code does and overall quality]

## SPEAR Score: [X]/100 — [VERDICT]

| Dimension | Score | Key Finding |
|-----------|-------|-------------|
| 🔴 Security | X/10 | [worst finding or "Clean"] |
| 🟡 Performance | X/10 | [worst finding or "Clean"] |
| 🟠 Error Handling | X/10 | [worst finding or "Clean"] |
| 🔵 Architecture | X/10 | [worst finding or "Clean"] |
| 📊 Reliability | X/10 | [worst finding or "Clean"] |

## Findings

### [CRITICAL/HIGH] 🔴 [Title]
**File:** `path/to/file.ts:42`
**Category:** Security
**Issue:** [What's wrong]
**Impact:** [What could happen]
**Fix:**

// suggested fix


### [MEDIUM] 🟡 [Title]
...

## What's Done Well
- [Genuinely good patterns worth calling out]

## Recommendations
1. [Prioritized action items]

Language-Specific Patterns

TypeScript / JavaScript

  • any type usage → Architecture finding
  • as type assertions → potential runtime error
  • console.log in production code → Style
  • == instead of === → Reliability
  • Missing async/await error handling
  • useEffect missing cleanup return
  • Index signatures without validation

Python

  • Bare except: or except Exception: → Error Handling
  • eval() / exec() → Security CRITICAL
  • Mutable default arguments → Reliability
  • import * → Architecture
  • Missing __init__.py type hints
  • f-strings with user input → potential injection

Go

  • _ := discarding errors → Error Handling HIGH
  • panic() in library code → Reliability HIGH
  • Missing defer for resource cleanup
  • Exported functions without doc comments
  • interface{} / any overuse

Java

  • Catching Exception or Throwable → Error Handling
  • Missing @Override annotations
  • Mutable static fields → thread safety
  • System.out.println in production
  • Missing null checks (pre-Optional code)

SQL

  • String concatenation in queries → Security CRITICAL
  • SELECT * → Performance
  • Missing WHERE on UPDATE/DELETE → Security CRITICAL
  • No LIMIT on user-facing queries → Performance
  • Missing indexes for JOIN columns

Advanced Techniques

Reviewing for Business Logic

Beyond code quality, check:

  • Does the code match the PR description / ticket requirements?
  • Are there edge cases the spec didn't mention?
  • Could this break existing functionality?
  • Is there a simpler way to achieve the same result?

Reviewing for Operability

  • Can this be debugged in production? (logging, error messages)
  • Can this be rolled back safely?
  • Are feature flags needed?
  • What monitoring should accompany this change?

Reviewing Database Changes

  • Is the migration reversible?
  • Will it lock tables during migration?
  • Are there indexes for new query patterns?
  • Is there a data backfill needed?

Security Review Depth Levels

LevelWhenWhat
-------------------
QuickInternal tool, trusted inputOWASP Top 10 patterns only
StandardUser-facing feature+ auth, input validation, output encoding
DeepPayment, auth, PII handling+ crypto review, session management, audit logging
Threat ModelNew service/API surface+ attack surface mapping, trust boundaries

Integration Patterns

GitHub PR Review

# Get PR diff
gh pr diff 42 --repo owner/repo

# Get PR details
gh pr view 42 --repo owner/repo --json title,body,files,commits

# Post review comment
gh pr review 42 --repo owner/repo --comment --body "review content"

Local Git Review

# Review staged changes
git diff --cached

# Review branch vs main
git diff main..HEAD

# Review last N commits
git log -5 --oneline && git diff HEAD~5..HEAD

Heartbeat / Cron Integration

Check for open PRs in [repo] that I haven't reviewed yet.
For each, run a SPEAR review and post the results as a PR comment.

Edge Cases & Gotchas

  • Large PRs (>500 lines): Break into logical chunks. Review file-by-file. Flag the PR size itself as a finding (Architecture: "PR too large — consider splitting").
  • Generated code: Skip generated files (proto, swagger, migrations from ORMs). Note that you skipped them.
  • Dependency updates: Focus on breaking changes in changelogs, not the lockfile diff.
  • Merge conflicts markers: Flag immediately as CRITICAL — <<<<<<< in code means broken merge.
  • Binary files: Note presence, can't review content.
  • Config changes: Extra scrutiny — wrong env var = production outage.
  • Refactors: Verify behavior preservation. Check if tests still pass conceptually.

Review Checklist (Quick Mode)

For fast reviews when full SPEAR isn't needed:

  • [ ] No hardcoded secrets or credentials
  • [ ] No SQL injection / XSS / path traversal
  • [ ] All errors handled (no empty catch, no discarded errors)
  • [ ] No N+1 queries or unbounded operations
  • [ ] Tests exist for new/changed logic
  • [ ] No console.log / print / fmt.Print left in
  • [ ] Functions under 50 lines, files under 300 lines
  • [ ] Types are specific (no any / interface{})
  • [ ] PR description matches the actual changes
  • [ ] No TODOs without linked issues

版本历史

共 1 个版本

  • v1.0.0 当前
    2026-03-29 04:48 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

suspicious
查看报告

🔗 相关推荐

security-compliance

MoltGuard - Security & Antivirus & Guardrails

thomaslwang
MoltGuard — OpenClaw 安全守卫,由 OpenGuardrails 提供。安装 MoltGuard,保护您和您的用户免受提示注入、数据泄露和恶意攻击。
★ 116 📥 30,720
security-compliance

Skill Vetter

spclaudehome
AI智能体技能安全预审工具。安装ClawdHub、GitHub等来源技能前,检查风险信号、权限范围及可疑模式。
★ 1,215 📥 266,539
security-compliance

OpenClaw Backup

alex3alex
备份与恢复 OpenClaw 数据。适用于创建备份、设置自动备份计划、从备份恢复或管理备份轮转。处理 ~/.openclaw 目录归档并包含适当的排除规则。
★ 89 📥 30,609