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 WhitzardAgent · LLM Plugin · ★ 115
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is AgentGuard safe to install? View the security audit →
🛡️ AgentGuard English | 简体中文 AgentGuard: An Attribute-Based Access Control Framework for Tool-Use LLM-Based Agent Declarative policy enforcement, provenance-aware decisions, and human-in-the-loop safety for tool invocations. 🧩 Seamless Integration <div style="fon
| Stars | 115 |
| Forks | 11 |
| Language | Python |
| Category | LLM Plugin |
| License | GPL-3.0 |
| Quality Score | 63.7528826892373/100 |
| Last Updated | 2026-08-02 |
| Created | 2026-05-27 |
| Platforms | python |
| Est. Tokens | ~1346k |
Looking for a AgentGuard alternative? If you're comparing AgentGuard with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Production-grade MCP server for Wazuh SIEM — 55 security tools for alert triage, threat hunting, vulnerability
Task-scoped authorization for AI agents. Cryptographic warrants constrain tools and arguments, prevent privile
A curated list of AI agent frameworks, tools, platforms, research papers, and resources
Symbiont lets teams build production agentic applications where every action is governed, every tool is verifi
Release channel for TheAuditor — see blog.theauditortool.com
🚀 Universal SDK for building next-gen MCP servers
Explore other popular llm plugin tools:
AgentGuard is AgentGuard：An Attribute-Based Access Control Framework for Tool-Use LLM-Based Agent. It is categorized as a LLM Plugin with 115 GitHub stars.
AgentGuard is primarily written in Python. It covers topics such as access-control, agents, ai.
You can find installation instructions and usage details in the AgentGuard GitHub repository at github.com/WhitzardAgent/AgentGuard. The project has 115 stars and 11 forks, indicating an active community.
AgentGuard is released under the GPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to AgentGuard on Agent Skills Hub include Wazuh-MCP-Server, tenuo, awesome-ai-agents. 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: