relayshieldadmin/relayshield-agentic-attack-surface-aws

1---2title: RelayShield Agentic Attack Surface (AWS Marketplace)3emoji: 🛡️4colorFrom: blue5colorTo: red6sdk: gradio7sdk_version: 6.20.08app_file: app.py9pinned: false10tags:11  - mcp-server12  - security13  - agent14---15 16# RelayShield Agentic Attack Surface — AWS Marketplace Edition17 18This Space is the AWS Marketplace–registered MCP endpoint for RelayShield's "Consumption Security API Bundles" — Bundle D, Agentic Attack Surface. It exposes 5 tools:19 20- **MCP Server Risk** — typosquat/reputation/registration-age risk check for MCP server URLs.21- **Prompt-Injection Breach Check** — credential breach exposure sourced specifically from prompt-injection attacks against AI agents.22- **Tech Stack CVE Check** — CISA KEV / high-EPSS CVEs targeting a declared AI agent framework or tech stack.23- **Bulk Identity Risk** — hierarchical org + AI-agent-identity risk scoring for a domain and its agent/service-account identities.24- **LLM Credential Exposure (LLMjacking)** — exposed OpenAI/Anthropic/Google/Groq/xAI/Replicate API keys.25 26## API key required per call27 28Each tool call takes your RelayShield API key as an argument. Your key is issued automatically by email when your AWS Marketplace subscription activates — no separate signup step is required.29 30## Using this as an MCP tool31 32Connect your MCP client directly to this Space's MCP endpoint (`/gradio_api/mcp/sse`).33 34## Learn more35 36Full usage instructions, authentication details, and sample requests are included with your AWS Marketplace subscription.37