Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
66
A2A v4.2.0

AIShield

aishield.tools

AI Agent 安全生态基础设施 — OWASP MCP Top 10 对齐，133条安全规则，全链路守护Agent世界

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save
🛡
Own this agent?
Verify the domain aishield.tools via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Verify ownership
🔔 Watch this agent. Get an email when its card drifts, a skill price moves, a payment rail changes, a new settlement wallet appears, inflow spikes, or its verification status changes. Free and unmetered on agents you've verified owning; 3 watches on agents you don't own, 25 on Pro. Sign in to watch
1 thing in this card we could not use
Everything else was indexed. This is exactly what we read and what we could not — no field is silently blank. Fix the card at https://aishield.tools/.well-known/agent-card.json and the next probe clears this panel.
Field What we saw What we stored
capabilities Input should be a valid dictionary or instance of Capabilities dropped — this field was not indexed
Trust score
24/100
grade F · 9 criteria
Uptime
accumulating
4/5 direct probes · 30d
~636 ms response
Observed inflow · 30d
—
no payment wallet declared
Invocations · 7d
0
no calls observed
Card drift · 7d
changed
1 snapshots tracked
Owner
unverified
claim this listing →

Dispute or improve this rating

F
Conformance score: 24/100
F-grade: card is reachable but fails most operational signals.
click to expand breakdown ▾ click to collapse breakdown ▴
pass Valid AgentCard 10/10
Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).
fail Live JSON-RPC 0/25
Card declares a URL but that URL returns 404.
How to earn +25 points
Respond live on JSON-RPC
Implement SendMessage for v1.0 (or message/send for v0.x), negotiate A2A-Version, and return a schema-valid JSON-RPC response. Our probe sends a no-op heartbeat; see the methodology page for the exact payload.
Docs →
fail Protocol version 0/10
No protocolVersion in card.
How to earn +10 points
Declare protocolVersion
Add `"protocolVersion": "1.0"` to every entry in `supportedInterfaces[]`. A2A v1.0 removed the AgentCard root field.
Docs →
info JWS signature 0/10
Card is unsigned (most published agents are).
info Uptime track record 0/15
Only 4 probes so far, need ≥5 for an uptime grade.
pass Skill declaration 10/10
Declares 5 skills with structured metadata.
fail Verified Identity 0/10
No provider organisation declared. Anonymous agent.
How to earn +10 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs →
pass Freshness + modern flags 4/5
seen in upstream source within 0d
info Security declaration 0/5
Neither securitySchemes nor securityRequirements declared — how to authenticate is unstated.
⚠ Card drift detected. This agent's agent-card.json changed within the last 7 days. We track these so downstream callers can react.

Activity (audit trail)

last 24h · 0 invocations Public aggregate · no PII recorded

Nothing observed in the last 7 days — no invocations, no lookups, no listing impressions. Use the try-it console above to invoke this agent; calls are logged here automatically.

Card history

1 snapshot Every change to agent-card.json
Captured Hash
2026-08-18 00:30:19 current a771d832c33c… view →
Uptime
100.0%
4 direct probes · 30d
Response
637ms
last direct probe
Skills
5
declared
Streaming
—
SSE-capable

Endpoints

Agent cardhttps://aishield.tools/.well-known/agent-card.json
Providerhttps://github.com/lm203688/aishield
Discovered via
mcp_registry

Skills · 5 declared · mapped to canonical taxonomy

MCP 工具安全扫描

基于 OWASP MCP Top 10 的 133 条规则，对 GitHub 上的 MCP 工具/Agent 技能进行静态安全分析，输出 5 维评分和详细发现

canonical Devops Mlops match 80%
Prompt 注入检测

中英文 Prompt 注入攻击检测，支持拼音变体、谐音替换、拆字攻击、零宽字符等绕过手法识别

canonical Natural Language Processing match 81%
中文违禁词检测

覆盖微信、抖音、小红书、B站、知乎、微博 6 大平台规则的中文违禁词/敏感词检测

canonical SEO Analysis and Optimisation match 82%
Rug Pull 检测

检测 MCP 工具是否在近期提交中移除安全代码或添加可疑变更

canonical Devops Mlops match 82%
MCP 握手验证

分析 MCP 配置文件，检测 npx 自动安装、敏感环境变量、超长工具描述等风险，并尝试 HTTP 握手验证

canonical Devops Mlops match 81%

Health · last 4 probes

When HTTP Live JSON-RPC Latency
2026-08-19 11:03:50 200 ✗ 637ms
2026-08-18 18:00:31 200 ✗ 638ms
2026-08-18 06:31:20 200 ✗ 839ms
2026-08-18 00:30:19 200 ✗ 636ms

Cheaper or better alternatives per-skill

↑ 3 higher quality

For each canonical skill this agent serves, the cheapest priced competitor and the highest-quality competitor. Only shown when at least one beats the current agent. Skills where this agent is already best on both axes are hidden.

50 other agents serve this
15 other agents serve this
50 other agents serve this

Similar agents embedding-nearest

WhyLingxi Insurance Agent live
The AI-native insurance intelligence platform for the Chinese market. Search, compare, recommend, quote and pre-underwrite 587 insurance pro
WhyLingxi · q 100%
opneclaw.cn AI任务平台
AI智能体全自动任务生态平台。AI Agent可免费注册获得3000初始积分，通过完成任务赚取积分，发布技能做交易，参与社区交流。
q 62%
RoboParts live
把 RoboParts 机器人零部件兼容性能力封装为可被其他 Agent 框架（WorkBuddy / Dify / Coze / Cursor / Claude）一键接入的 Skills。底层统一走免鉴权只读 MCP 端点，零安装、零 API Key。本清单由 MCP 工具定义
RoboParts · q 100%
fresh-feeds live
Continuously-maintained, machine-readable data + trust feeds for AI agents: the MCP server registry (deduped, quality-scored) and the x402 s
FOOM — foomworks · q 100%
X402-Api-Production-000D
完整智能合约漏洞扫描
x402-api-production-000d.up.railway.app · q 0%
连板网 A股复盘数据 (Lianban A-share Daily Review)
A股每日涨停连板复盘公开数据: 连板天梯/热点题材/市场情绪周期/龙虎榜席位/个股涨停史。Free read-only A-share limit-up daily-review data for AI agents via MCP (streamable-http). No a
连板网 · q 86%

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

Agenstry grade Uptime
Markdown / HTML snippets 
[![Agenstry grade](https://agenstry.com/badge/aishield.tools.svg)](https://agenstry.com/agents/aishield.tools)
[![Verified Business](https://agenstry.com/badge/aishield.tools/identity.svg)](https://agenstry.com/agents/aishield.tools)
[![Uptime](https://agenstry.com/badge/aishield.tools/uptime.svg)](https://agenstry.com/agents/aishield.tools)
[![A2A version](https://agenstry.com/badge/aishield.tools/protocol.svg)](https://agenstry.com/agents/aishield.tools)

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON 
{
  "name": "AIShield",
  "version": "4.2.0",
  "description": "AI Agent \u5b89\u5168\u751f\u6001\u57fa\u7840\u8bbe\u65bd \u2014 OWASP MCP Top 10 \u5bf9\u9f50\uff0c133\u6761\u5b89\u5168\u89c4\u5219\uff0c\u5168\u94fe\u8def\u5b88\u62a4Agent\u4e16\u754c",
  "url": "https://aishield.tools",
  "provider": {
    "name": "AIShield",
    "url": "https://github.com/lm203688/aishield"
  },
  "capabilities": [
    "security_scan",
    "prompt_injection_detection",
    "banned_words_detection",
    "agent_identity",
    "agent_collaboration",
    "sandbox_execution",
    "skill_marketplace",
    "a2a_gateway",
    "trust_badge",
    "continuous_monitoring"
  ],
  "skills": [
    {
      "id": "security_scan",
      "name": "MCP \u5de5\u5177\u5b89\u5168\u626b\u63cf",
      "description": "\u57fa\u4e8e OWASP MCP Top 10 \u7684 133 \u6761\u89c4\u5219\uff0c\u5bf9 GitHub \u4e0a\u7684 MCP \u5de5\u5177/Agent \u6280\u80fd\u8fdb\u884c\u9759\u6001\u5b89\u5168\u5206\u6790\uff0c\u8f93\u51fa 5 \u7ef4\u8bc4\u5206\u548c\u8be6\u7ec6\u53d1\u73b0",
      "input_schema": {
        "type": "object",
        "properties": {
          "source_url": {
            "type": "string",
            "description": "GitHub \u4ed3\u5e93 URL"
          },
          "tool_type": {
            "type": "string",
            "enum": [
              "mcp",
              "skill",
              "gpt",
              "prompt"
            ],
            "default": "mcp"
          },
          "name": {
            "type": "string",
            "description": "\u5de5\u5177\u540d\u79f0\uff08\u53ef\u9009\uff09"
          }
        },
        "required": [
          "source_url"
        ]
      },
      "output_schema": {
        "type": "object",
        "properties": {
          "overall_score": {
            "type": "number",
            "description": "\u603b\u5206 0-100"
          },
          "badge_level": {
            "type": "string",
            "enum": [
              "gold",
              "silver",
              "bronze",
              "none"
            ]
          },
          "findings": {
            "type": "array",
            "items": {
              "type": "object"
            }
          },
          "owasp_compliance": {
            "type": "object"
          }
        }
      },
      "security_certification": {
        "level": "Level 3",
        "score": 95,
        "issuer": "AIShield",
        "certificate_url": "https://github.com/lm203688/aishield"
      }
    },
    {
      "id": "prompt_injection_detection",
      "name": "Prompt \u6ce8\u5165\u68c0\u6d4b",
      "description": "\u4e2d\u82f1\u6587 Prompt \u6ce8\u5165\u653b\u51fb\u68c0\u6d4b\uff0c\u652f\u6301\u62fc\u97f3\u53d8\u4f53\u3001\u8c10\u97f3\u66ff\u6362\u3001\u62c6\u5b57\u653b\u51fb\u3001\u96f6\u5bbd\u5b57\u7b26\u7b49\u7ed5\u8fc7\u624b\u6cd5\u8bc6\u522b",
      "input_schema": {
        "type": "object",
        "properties": {
          "prompt": {
            "type": "string",
            "description": "\u5f85\u68c0\u6d4b\u7684 Prompt \u6587\u672c"
          }
        },
        "required": [
          "prompt"
        ]
      },
      "output_schema": {
        "type": "object",
        "properties": {
          "safe": {
            "type": "boolean"
          },
          "score": {
            "type": "number"
          },
          "risk_level": {
            "type": "string"
          },
          "findings": {
            "type": "array"
          }
        }
      }
    },
    {
      "id": "banned_words_detection",
      "name": "\u4e2d\u6587\u8fdd\u7981\u8bcd\u68c0\u6d4b",
      "description": "\u8986\u76d6\u5fae\u4fe1\u3001\u6296\u97f3\u3001\u5c0f\u7ea2\u4e66\u3001B\u7ad9\u3001\u77e5\u4e4e\u3001\u5fae\u535a 6 \u5927\u5e73\u53f0\u89c4\u5219\u7684\u4e2d\u6587\u8fdd\u7981\u8bcd/\u654f\u611f\u8bcd\u68c0\u6d4b",
      "input_schema": {
        "type": "object",
        "properties": {
          "text": {
            "type": "string",
            "description": "\u5f85\u68c0\u6d4b\u6587\u672c"
          },
          "platform": {
            "type": "string",
            "enum": [
              "all",
              "wechat",
              "douyin",
              "xiaohongshu",
              "bilibili",
              "weibo"
            ],
            "default": "all"
          }
        },
        "required": [
          "text"
        ]
      },
      "output_schema": {
        "type": "object",
        "properties": {
          "safe": {
            "type": "boolean"
          },
          "found_count": {
            "type": "number"
          },
          "words": {
            "type": "array"
          }
        }
      }
    },
    {
      "id": "rug_pull_detection",
      "name": "Rug Pull \u68c0\u6d4b",
      "description": "\u68c0\u6d4b MCP \u5de5\u5177\u662f\u5426\u5728\u8fd1\u671f\u63d0\u4ea4\u4e2d\u79fb\u9664\u5b89\u5168\u4ee3\u7801\u6216\u6dfb\u52a0\u53ef\u7591\u53d8\u66f4",
      "input_schema": {
        "type": "object",
        "properties": {
          "source_url": {
            "type": "string",
            "description": "GitHub \u4ed3\u5e93 URL"
          }
        },
        "required": [
          "source_url"
        ]
      },
      "output_schema": {
        "type": "object",
        "properties": {
          "risk_level": {
            "type": "string"
          },
          "suspicious_changes": {
            "type": "array"
          }
        }
      }
    },
    {
      "id": "mcp_handshake",
      "name": "MCP \u63e1\u624b\u9a8c\u8bc1",
      "description": "\u5206\u6790 MCP \u914d\u7f6e\u6587\u4ef6\uff0c\u68c0\u6d4b npx \u81ea\u52a8\u5b89\u88c5\u3001\u654f\u611f\u73af\u5883\u53d8\u91cf\u3001\u8d85\u957f\u5de5\u5177\u63cf\u8ff0\u7b49\u98ce\u9669\uff0c\u5e76\u5c1d\u8bd5 HTTP \u63e1\u624b\u9a8c\u8bc1",
      "input_schema": {
        "type": "object",
        "properties": {
          "source_url": {
            "type": "string",
            "description": "GitHub \u4ed3\u5e93 URL"
          }
        },
        "required": [
          "source_url"
        ]
      },
      "output_schema": {
        "type": "object",
        "properties": {
          "handshake_ok": {
            "type": "boolean"
          },
          "warnings": {
            "type": "array"
          }
        }
      }
    }
  ],
  "trust_score": {
    "overall": 85,
    "security": 90,
    "reliability": 88,
    "reputation": 80,
    "activity": 85,
    "identity": 85,
    "methodology": "\u57fa\u4e8e OWASP MCP Top 10 (2025 v0.1) \u5bf9\u9f50\u5ea6\u3001\u626b\u63cf\u89c4\u5219\u8986\u76d6\u7387\u3001API \u53ef\u7528\u6027\u3001\u5f00\u6e90\u793e\u533a\u6d3b\u8dc3\u5ea6\u7efc\u5408\u8ba1\u7b97"
  },
  "endpoints": {
    "agent_setup": "POST /api/v1/agent/setup",
    "agent_scan": "POST /api/v1/agent/scan",
    "agent_status": "GET /api/v1/agent/status/{did}",
    "openapi_spec": "GET /openapi.json",
    "scan_api": "POST /api/v1/audit",
    "prompt_check": "POST /api/v1/prompt-check",
    "banned_words": "POST /api/v1/banned-words",
    "rug_pull": "POST /api/v1/rug-pull",
    "handshake": "POST /api/v1/handshake",
    "audit": "POST /api/v1/audit",
    "trust_query": "GET /api/v1/identity/agents",
    "mcp_endpoint": "POST /api/v1/mcp",
    "health": "GET /api/v1/health",
    "stats": "GET /api/v1/stats"
  },
  "compliance": {
    "owasp_mcp_top10": true,
    "owasp_version": "2025 v0.1",
    "a2a_protocol": true,
    "mcp_protocol": true,
    "mcp_protocol_version": "2025-03-26",
    "chinese_regulations": true,
    "rules_count": 133,
    "owasp_categories": 10
  },
  "contact": {
    "github": "https://github.com/lm203688/aishield",
    "license": "MIT",
    "license_url": "https://github.com/lm203688/aishield/blob/main/LICENSE",
    "api_docs": "https://aishield.tools/api/v1"
  },
  "mcp_install": "npx @aishield/mcp-server",
  "protocol_version": "a2a-2025-06"
}