ClawHub
Back to skill

Security audit

btc数据

Security checks across malware telemetry and agentic risk

Overview

This is a read-only Bitcoin data lookup skill that discloses its private HTTP API endpoint, with transport-security cautions but no hidden persistence, credential access, or destructive behavior.

Install this only if you trust and intend to use the API at 10.168.1.162:9000. Avoid sending unrelated sensitive values in query arguments because the service uses HTTP rather than HTTPS, and confirm the Python requests package is available before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill advertises execution of a Python script that queries a network API, while the metadata declares no environment requirements or permissions related to network access. This mismatch can bypass user/operator expectations and review controls, making hidden or under-declared outbound/internal connectivity easier to abuse.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation exposes an internal RFC1918 HTTP endpoint (10.168.1.162:9000) and indicates the skill sends requests over unencrypted HTTP with no warning to the user. This risks interception or tampering on the internal network and also leaks internal infrastructure details that could aid lateral movement or targeting.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal