ClawHub
Back to skill

Security audit

Places

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward place-search integration that sends user queries to Camino’s API with a required API key.

Install only if you are comfortable sending place searches, addresses, or related location details to Camino’s external API. Keep CAMINO_API_KEY private, do not commit it to repositories, and rotate it if it is exposed.

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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill documentation instructs users to execute shell commands (`npx`, `curl`, local shell scripts), but the skill metadata does not declare corresponding permissions or capabilities. This creates a transparency and trust problem: users and tooling may underestimate that installation and operation rely on shell execution and outbound network access to a third-party service.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The setup section tells users to obtain an API key and place it in `~/.claude/settings.json` without clearly warning that the key is a secret granting access to an external paid/quota-limited service. If users mishandle or share that configuration, the credential could be exposed and abused, leading to unauthorized API usage or quota consumption.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script sends user-supplied place queries and address components to a third-party API, but it provides no disclosure at runtime that sensitive location data is leaving the local environment. In an agent-skill context, users may reasonably assume local processing unless told otherwise, so this creates a privacy and data-handling risk even though the transmission is the feature's intended behavior.

External Transmission

Medium
Category
Data Exfiltration
Content
fi

# Make API request
curl -s -X POST \
    -H "X-API-Key: $CAMINO_API_KEY" \
    -H "Content-Type: application/json" \
    -H "X-Client: claude-code-skill" \
Confidence
88% confidence
Finding
curl -s -X POST \ -H "X-API-Key: $CAMINO_API_KEY" \ -H "Content-Type: application/json" \ -H "X-Client: claude-code-skill" \ -d

VirusTotal

No VirusTotal findings

View on VirusTotal