ClawHub
Back to skill

Security audit

Marktplaats

Security checks across malware telemetry and agentic risk

Overview

This Marktplaats skill mostly matches its purpose, but its detail-fetch feature can request any HTTP(S) URL, which is broader than a classifieds-search tool should need.

Install only if you are comfortable with the agent making outbound web requests. Use the detail feature only with Marktplaats listing URLs or Marktplaats VIP paths, and avoid letting untrusted page text or prompts supply --details URLs until the skill restricts fetching to Marktplaats domains.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
This is a mismatch because the description only mentions searching classifieds with filtering support, but the code also provides additional capabilities beyond search: it explores category trees and fetches/parses individual listing pages for detailed content. Those are material user-facing behaviors not represented in the declared description.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The function accepts any URL starting with 'http' and performs a network fetch, which can transmit system metadata such as IP/user agent to third-party hosts. While the code is documented as fetching listing details, there is no explicit warning, confirmation, or user-facing disclosure that arbitrary external URLs may be requested.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The code hard-codes toLocaleString('nl-NL') when rendering prices, which forces a specific locale regardless of user preference. This is a natural-language/locale policy concern because the skill does not offer locale choice or explain that it is intentionally region-specific.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.