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 cisco-ai-defense · Agent Tool · ★ 2.6k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is skill-scanner safe to install? View the security audit →
Skill Scanner A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns. Combines pattern-based detection (YAML + YARA), LLM-as-a-judge, and behavioral dataflow analysis to maximize detection coverage of probable threats while minimizing false positives. Important: This scanner provides best-effort d
| Stars | 2,572 |
| Forks | 329 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 76.1915636396534/100 |
| Last Updated | 2026-10-03 |
| Created | 2026-01-29 |
| Platforms | python |
| Est. Tokens | ~17k |
Looking for a skill-scanner alternative? If you're comparing skill-scanner 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.
The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Sca
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
Connect any AI model to 1200+ integrations (MCP, CLI, API)
Security scanner for AI agents, MCP servers and agent skills.
AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function
Explore other popular agent tool tools:
skill-scanner is Security Scanner for Agent Skills. It is categorized as a Agent Tool with 2.6k GitHub stars.
skill-scanner is primarily written in Python. It covers topics such as agent, agent-skills, security.
You can find installation instructions and usage details in the skill-scanner GitHub repository at github.com/cisco-ai-defense/skill-scanner. The project has 2.6k stars and 329 forks, indicating an active community.
The top alternatives to skill-scanner on Agent Skills Hub include refly, AI-Infra-Guard, deepchat. 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: