ClawHub
Back to skill

Security audit

Context

Security checks across malware telemetry and agentic risk

Overview

This location-context skill appears coherent and purpose-aligned, but it sends the coordinates and context you provide to Camino's external API.

Install only if you are comfortable sending chosen coordinates, request context, optional weather parameters, and any trial signup email to Camino. Prefer a scoped or temporary API key and avoid sending unnecessarily precise or sensitive locations.

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 (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill documentation clearly instructs users to run shell commands (`curl`, `npx`, and local shell scripts), yet the metadata does not declare corresponding permissions or capabilities. This mismatch can mislead users and security tooling about what the skill actually requires, reducing transparency and making it easier for risky execution paths to be overlooked.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill sends precise latitude/longitude and an API key to a third-party remote service, and optionally includes contextual queries and weather-related requests, but it does not provide a clear privacy warning or consent guidance. Precise location data is highly sensitive and can reveal a user's whereabouts, routines, or associations if transmitted without explicit disclosure and user understanding.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The script transmits precise user-supplied location data to a third-party API, but it does not provide any in-script notice, consent mechanism, or data-minimization safeguards. Because location data is sensitive, sending it externally without explicit warning can create privacy and compliance risk even if the transmission is the core function of the skill.

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
93% 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

External Transmission

Medium
Category
Data Exfiltration
Content
-H "Content-Type: application/json" \
    -H "X-Client: claude-code-skill" \
    -d "$INPUT" \
    "https://api.getcamino.ai/context" | jq .
Confidence
90% confidence
Finding
https://api.getcamino.ai/

VirusTotal

No VirusTotal findings

View on VirusTotal