ClawHub

Places

Security checks across malware telemetry and agentic risk

Overview

This skill is a normal Camino place-search helper that sends your place or address query to Camino’s API using your Camino API key.

Install only camino-places unless you have reviewed the wider Camino skill suite. Use a Camino API key intended for this integration, and avoid submitting sensitive home, workplace, or private location queries unless you are comfortable with Camino processing them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill documentation indicates it shells out to external binaries (`curl`, `jq`) via scripts, but it does not declare explicit permissions for shell/network execution beyond metadata requirements. This creates a capability transparency problem: users and hosting systems may not realize the skill can execute shell commands and send data externally, which weakens sandboxing and informed consent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script transmits user-supplied place queries and address components to a third-party service, but it does not provide any runtime disclosure, confirmation, or consent signal before sending potentially sensitive location data off-host. In an agent skill context, users may not realize that free-form queries or structured addresses are being exfiltrated to an external API, which creates a real privacy and data-handling risk even though the network call is the intended function of the skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal