claude-analysis

claude-analysis is a Penetration testing & red team skill for AI agents, published by Esonhugh in the claude-code repository on GitHub. Skillspace rates claude-analysis C (74/100) and it passed the safety scan; the rating is based on static analysis only.

当用户要求分析授权的当前项目下的 Claude Code 源码、official-claude/built-claude 二进制，或需要从 .bun / __BUN,__bun section 提取 cli.original.js、用 objdump/nm/otool 检查符号或 section、用 Frida 观察本地运行行为、用 webcrack/restringer 提升可读性、或用本 skill 的 scripts/claude_cch.py 复现授权请求样本的 cch checksum 时，应使用此 skill。若任务主要是 tmux/InteractiveTerminal、非交互 CLI、--debug-file、HTTP_PROXY/HTTPS_PROXY、SSE/WebSocket 或请求抓流调试，应改用 claude-debug skill。

Grade
C
Quality
74 / 100
Safety
Passed
GitHub stars
33

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubEsonhugh/claude-code

Our review

Architecture
88 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

More Penetration testing & red team skills

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.