ClawHub
Back to skill

Security audit

AFOL BrickLink

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed BrickLink API helper that needs user-provided OAuth credentials, with a minor permissions-documentation caveat.

Install only if you intend to connect the agent to BrickLink. Use narrowly scoped BrickLink API credentials, avoid sharing unrelated environment variables, and review any future version that adds broader account mutation or background behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill explicitly relies on environment variables for OAuth credentials and makes outbound API calls, but the manifest does not declare corresponding permissions. That creates a transparency and policy-enforcement gap: a host may expose env/network access without users realizing the skill needs them, or may be unable to enforce least privilege consistently.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.