agentic-attack-surface

Four AI-agent-specific security checks from RelayShield's Agentic Attack Surface: MCP server risk (typosquat/reputation/registration-age), prompt-injection breach detection, tech stack CVE exposure (CISA KEV/EPSS), and bulk identity risk scoring. Each call requires your own RelayShield API key — get one at api.relayshield.net/developers.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://agentic-attack-surface--relayshieldadmin.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "agentic-attack-surface": {
      "url": "https://agentic-attack-surface--relayshieldadmin.run.tools"
    }
  }
}

能力清单

工具	说明
check_mcp_server_risk	Check an MCP server URL for typosquat risk, presence in RelayShield's criminal IOC corpus, and domain-registration age. Returns a verdict (CRITICAL/HIGH/MEDIUM/LOW) with any findings.
check_prompt_injection_breach	Check an email address for credential exposure sourced specifically from prompt-injection attacks against AI agents, distinct from ordinary phishing/malware-sourced breaches.
check_tech_stack_cve	Check a declared AI agent framework / tech stack for CISA KEV or high-EPSS CVEs actively being exploited. Covers AI agent orchestration frameworks and common companion infrastructure.
check_bulk_identity_risk	Hierarchical org + AI-agent-identity risk scoring for a domain and up to 5 agent/service-account identities. A critically-exposed agent automatically elevates the organizational risk rating.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。