ClawHub
Back to skill

Security audit

alpinist-route-forecast

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says: fetch route-aware mountain weather, with disclosed coordinate sharing and local pace-profile storage.

Install only if you are comfortable sending route or summit coordinates to Open-Meteo and NOAA/NWS, and saving calibration history locally. On shared machines, avoid calibration or delete the local profile if trip timing or GPX paths are sensitive.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • 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
Findings (3)

Tainted flow: 'req' from urllib.request.urlopen (line 827, network input) → urllib.request.urlopen (network output)

Medium
Category
Data Flow
Content
# Step 2: Get hourly forecast
    try:
        req = Request(hourly_url, headers=headers)
        resp = urlopen(req, timeout=10)
        data = json.loads(resp.read())
        periods = data["properties"]["periods"]
    except Exception as e:
Confidence
84% confidence
Finding
resp = urlopen(req, timeout=10)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill documentation describes network access to multiple external weather services and local file creation/writes for the alpinist profile, but no explicit permissions are declared. This creates a transparency and policy gap: users or host systems may not realize the skill can transmit route coordinates externally and persist local data, which increases privacy and governance risk even if the behavior is part of the intended functionality.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
Trip calibration persistently writes a local profile containing route file paths and trip timing history without an explicit consent prompt or clear disclosure. In a shared environment, this can leak sensitive behavioral and location-related information and create privacy risk beyond user expectations.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.