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 Agent-Threat-Rule · MCP Server · ★ 399
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agent-threat-rules safe to install? View the security audit →
ATR — Agent Threat Rules Open detection rule format for AI agent security threats. AI Agent 威脅偵測規則的開放格式 A
| Stars | 399 |
| Forks | 60 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 69.4409492168605/100 |
| Open Issues | 56 |
| Last Updated | 2026-09-22 |
| Created | 2026-03-09 |
| Platforms | mcp, node |
| Est. Tokens | ~22k |
Looking for a agent-threat-rules alternative? If you're comparing agent-threat-rules with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, pro
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (
IAM for your AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, revi
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mappe
Explore other popular mcp server tools:
agent-threat-rules is Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merge. It is categorized as a MCP Server with 399 GitHub stars.
agent-threat-rules is primarily written in TypeScript. It covers topics such as agent-security, agent-threat-rules, ai-security.
You can find installation instructions and usage details in the agent-threat-rules GitHub repository at github.com/Agent-Threat-Rule/agent-threat-rules. The project has 399 stars and 60 forks, indicating an active community.
agent-threat-rules is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to agent-threat-rules on Agent Skills Hub include Adrian, agent-security-scanner-mcp, node9-proxy. 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: