ClawHub
Back to skill

Security audit

Relationship

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Camino API client for comparing two locations, with the main caution that it sends the coordinates you provide to Camino's service.

Install only if you are comfortable sending the exact coordinates you provide, plus your Camino API key for authentication, to api.getcamino.ai. Protect the API key stored in Claude settings and inspect the referenced GitHub repository before using the npx install path.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The skill claims to calculate spatial relationships, but the implementation sends the full user-supplied coordinates to a third-party API to perform the work. This is a material behavior gap because users may reasonably expect local computation for a simple geometry task, and the undisclosed remote delegation exposes potentially sensitive location data outside the local environment.

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The script reads an API key from the environment and performs outbound network access, but the manifest description alone does not justify or disclose this sensitive behavior. In a skill handling location data, hidden credential use plus external transmission increases privacy and trust risk because user data and secrets are involved in an operation that appears computationally simple.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script transmits user-provided start/end latitude and longitude to an external API without any explicit user-facing warning or consent mechanism. Location data can be sensitive, and silent submission to a remote service creates a privacy exposure that is more dangerous in this skill because exact coordinates are the primary input.

VirusTotal

No VirusTotal findings

View on VirusTotal