Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
alirezaaminzadeh 's Collections
SigmaForge
RefineryGuard
SOC Agent Traces
CVE-RiskRank
SecEmbed
AgentShield-Bench
SOC Agent Research Suite
Aria AI Operations Research Portfolio
CyberSOC AI Portfolio

AgentShield-Bench

updated Aug 9

Agent security benchmark for tool-calling and MCP environments — dataset, classifiers, secure agent pipeline, and interactive evaluation.

Upvote
-

  • Paused
    Agents

    AgentShield-Bench

    🛡

    Agent security benchmark for tool-calling & MCP

    Note Interactive benchmark demo


  • alirezaaminzadeh/agentshield-bench

    Viewer • Updated Aug 9 • 5.76k • 67

    Note 720 security scenarios


  • alirezaaminzadeh/agentshield-prompt-injection-classifier

    Text Classification • 22.7M • Updated Sep 15 • 11

    Note Injection classifier


  • alirezaaminzadeh/agentshield-tool-risk-classifier

    Text Classification • 22.7M • Updated Sep 15 • 6

    Note Tool risk classifier


  • alirezaaminzadeh/agentshield-content-trust-classifier

    Text Classification • 22.7M • Updated Sep 15 • 6

    Note Content trust classifier


  • alirezaaminzadeh/agentshield-policy-decision-model

    Text Classification • 22.7M • Updated Sep 15 • 7 • 1

    Note Policy decision model


  • alirezaaminzadeh/agentshield-secure-agent

    Text Generation • Updated Aug 9

    Note Secure agent pipeline

Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs