No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by 0rangec3t · AI Tool · ★ 286
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Black-cat safe to install? View the security audit →
Black cat 一只头戴女巫帽的魔法黑猫。 Claude code Redteam skill 做这个 Skill 的原因 最近一直在看自动化渗透相关，尝试性写了几个框架，但是最后效果都不太满意。相反，之前当玩具写的 Skill 放在 Claude Code 里面，效果却出乎意料地好。 本 Skill 主要使用假设—证据驱动，为了模仿人在真实场景下的渗透测试。 与市面上所有 pentest skill 的本质区别 市面上的 pentest skill 都是 Pipeline（流水线）：Recon → Scan → Exploit → Report。每个 phase 绑定固定工具，失败就跳到下一步，没有回边。 我们的设计是 State Machine（状态机）：RECON ⇄ ENUMERATE ⇄ VALIDATE。证伪、失败和新发现都可以回到前面的状态重新开始。横向移动成功后在新目标上重启 RECON。 v1.1.0 更新内容 调整：授权 Gate 一次性确认 授权在加载 skill 时确认一次，此后整个会话不再重复确认；超出锁定范围或存在歧义的操作默认先做，仅在授权文档明确禁止时才不做。 消除了中途越界时的暂停询问流程，减少打断。 新增：provisional 裁决 + REPORT 机器关口 caseledger.py verdict --statu
| Stars | 286 |
| Forks | 35 |
| Language | Python |
| Category | AI Tool |
| Quality Score | 59.1653799959007/100 |
| Open Issues | 1 |
| Last Updated | 2026-08-03 |
| Created | 2026-07-30 |
| Platforms | claude-code, python |
| Est. Tokens | ~16k |
These tools work well together with Black-cat for enhanced workflows:
Looking for a Black-cat alternative? If you're comparing Black-cat with other ai tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Watchtower is a simple AI-powered penetration testing automation CLI tool that leverages LLMs and LangGraph to
AI Powered penetration testing Platform for offensive security research
一款证据驱动的 FOFA 资产测绘智能体：支持自然语言侦察、AI 反思、CLI / MCP / Skill / REST API，以及经人工审批的 Nuclei 扫描。
Open-source Claude Code skills, agents, and slash commands for AI-powered penetration testing, bug bounty hunt
EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing struct
MCP-native security automation workbench (SDK + CLI + MCP) — authorized testing + static AI/MCP attack-surface
Explore other popular ai tool tools:
Black-cat is Claude Code RedTeam Skill — Hypothesis-Driven Cognitive Architecture。一个假设-证据驱动的红队skill. It is categorized as a AI Tool with 286 GitHub stars.
Black-cat is primarily written in Python. It covers topics such as pentest, pentest-tools, red-team.
You can find installation instructions and usage details in the Black-cat GitHub repository at github.com/0rangec3t/Black-cat. The project has 286 stars and 35 forks, indicating an active community.
The top alternatives to Black-cat on Agent Skills Hub include watchtower, nyxstrike, FofaMap. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: