ClawHub
Back to skill

Security audit

BrickEconomy

Security checks across malware telemetry and agentic risk

Overview

This read-only BrickEconomy skill can access private collection and sales data when requested, but that access is disclosed and fits its valuation purpose.

Install only if you are comfortable giving the skill a BrickEconomy API key and allowing requested collection or sales-ledger data to appear in the agent context. Prefer scoped summaries for privacy, avoid untrusted base-url overrides, and do not use it for marketplace writes or purchase actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The OpenAPI description explicitly states the API provides access to a user's personal collection data, while the skill metadata emphasizes valuation and analysis from verified Brick Directory references. That mismatch expands the accessible data surface to authenticated personal inventory and history, increasing the risk of over-collection or unintended exposure if the agent uses broader endpoints than users expect.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The spec includes endpoints for full set collections, minifig collections, and sales ledger access without any documented scope restrictions, purpose limitations, or exclusion conditions. In an agent setting, these endpoints could expose detailed ownership, purchase, sale, and valuation history far beyond what is needed for a narrow valuation task, creating privacy and profiling risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.