by pashov · Agent Tool · ★ 651
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 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 | 651 |
| Forks | 129 |
| Category | Agent Tool |
| Quality Score | 42/100 |
| Open Issues | 2 |
| Last Updated | 2026-11-13 |
| Created | 2026-03-12 |
| Est. Tokens | ~8k |
Web3 Security Tools Hub A curated list of AI tools for smart-contract security. Built and maintained by pashov.com. How to choose: 🛠️ Want something you install and run yourself? → Free & Open Source 💼 Want a managed platform or service? → Paid & Closed Source 🔤 Looking for your language? → jump straight from the Contents below.
These tools work well together with ai-web3-security for enhanced workflows:
Looking for a ai-web3-security alternative? If you're comparing ai-web3-security with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A security scanner for your LLM agentic workflows
AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-cal
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do
18 Claude Code skill files for smart contract security — built from 2,749 Immunefi reports, 681 DeFiHack repro
A curated list of AI-powered coding tools
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: