AI-Infra-Guard — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 Tencent · MCP Server · ★ 6.4k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is AI-Infra-Guard safe to install? View the security audit →

About AI-Infra-Guard

Documentation | 中文 <a href="https://www.blackhat.com/eu-25/arsenal/schedule/index

agentaibenchmarkinfrajailbreakllmmcpopenclawred-teamsafety

Quick Facts

Stars6,441
Forks595
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score63.005055242275/100
Open Issues33
Last Updated2026-09-18
Created2024-12-25
Platformsmcp, python
Est. Tokens~8430k

Compatible Skills

These tools work well together with AI-Infra-Guard for enhanced workflows:

  • fuzzforge_ai — semantic(0.15)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)
  • Auditor — semantic(0.15)+complementary+rare_topics+same_lang+similar_pop+shared_platform (59%)
  • skill-scanner — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (53%)
  • moonshot — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (53%)
  • agentic-radar — semantic(0.36)+rare_topics+same_lang+similar_pop+shared_platform (51%)

AI-Infra-Guard alternative? Top 6 similar tools

Looking for a AI-Infra-Guard alternative? If you're comparing AI-Infra-Guard 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.

  • CyberStrike by CyberStrikeus · ⭐ 1.9k

    Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models,

  • Anthropic-Cybersecurity-Skills by mukul975 · ⭐ 31.8k

    817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE

  • cursor-talk-to-figma-mcp by grab · ⭐ 7.0k

    TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c

  • deepchat by ThinkInAIXYZ · ⭐ 6.3k

    🐬DeepChat - A smart assistant that connects powerful AI to your personal world

  • openpencil by ZSeven-W · ⭐ 6.0k

    The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. De

  • PPTAgent by icip-cas · ⭐ 5.0k

    An Agentic Framework for Reflective PowerPoint Generation

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is AI-Infra-Guard?

AI-Infra-Guard is A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.. It is categorized as a MCP Server with 6.4k GitHub stars.

What programming language is AI-Infra-Guard written in?

AI-Infra-Guard is primarily written in Python. It covers topics such as agent, ai, benchmark.

How do I install or use AI-Infra-Guard?

You can find installation instructions and usage details in the AI-Infra-Guard GitHub repository at github.com/Tencent/AI-Infra-Guard. The project has 6.4k stars and 595 forks, indicating an active community.

What license does AI-Infra-Guard use?

AI-Infra-Guard is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to AI-Infra-Guard?

The top alternatives to AI-Infra-Guard on Agent Skills Hub include CyberStrike, Anthropic-Cybersecurity-Skills, cursor-talk-to-figma-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools