ClawHub
Back to skill

Security audit

graph-polymarket-mcp

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only Polymarket data MCP server, with the main caution that its optional HTTP/SSE mode is unauthenticated and can spend the user's Graph API quota if exposed.

Use the default stdio transport for local agents. If enabling --http or --http-only, do not expose the port to untrusted networks without localhost binding, firewalling, and authentication or a protected reverse proxy, because anyone who reaches it can run the read-only tools and consume your GRAPH_API_KEY quota.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
### OpenClaw / Remote Agents (SSE)

> **The SSE transport has no authentication.** Anyone who can reach the port can call every tool,
> and those calls spend *your* `GRAPH_API_KEY` quota. `--http` binds `0.0.0.0` inside a container,
> so publish it to `127.0.0.1` on the host and put a reverse proxy with TLS and auth in front of
> anything reachable off-box. For local agents, prefer the default stdio transport — it has no
Confidence
98% confidence
Finding
call every tool

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
smithery.yaml:16