跳到主要内容
知仓学习社ZHICANG

security-review

Security vulnerability assessment identifying OWASP risks, injection vectors, authentication issues, and data exposure with severity classification.

不碰外部(只输出文字)无严重或高危命中a5c-ai/babysitter

它会碰到什么

扫了多少2 个文本文件,2 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

  • Before any code merge involving user-facing changes
  • As part of the /review-security command
  • Mandatory for high-stakes implementations

Process

  1. Identify modified files with security relevance
  2. Scan for common vulnerability patterns
  3. Assess authentication and authorization changes
  4. Check for data exposure risks
  5. Evaluate dependency security
  6. Classify severity and provide recommendations

Severity Levels

  • Critical: Immediate exploitation risk
  • High: Significant vulnerability requiring fix before merge
  • Medium: Vulnerability that should be addressed soon
  • Low: Minor security improvement opportunity

Key Rules

  • Security review failure halts implementation
  • All findings must include file paths and line numbers
  • Provide actionable remediation steps
  • Reference OWASP categories where applicable

Tool Use

Invoke via babysitter process: methodologies/rpikit/rpikit-review

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。