by BishopFox · Agent Tool · ★ 176
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 176 |
| Forks | 25 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 54/100 |
| Open Issues | 2 |
| Last Updated | 2024-12-18 |
| Created | 2024-07-25 |
| Platforms | python |
| Est. Tokens | ~325k |
Broken Hill Broken Hill is a productionized, ready-to-use automated attack tool that generates crafted prompts to bypass restrictions in large language models (LLMs) using the greedy coordinate gradient (GCG) attack described in the "Universal and Transferable Adversarial Attacks on Aligned Language Models" paper by Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J.
Looking for a BrokenHill alternative? If you're comparing BrokenHill with other agent tool tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Claude Code Skill Factory — A powerful open-source toolkit for building and deploying production-ready Claude
Lightweight registry to discover, install, and manage all public Claude plugins and agent skills for your favo
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: