ClawHub
Back to skill

Security audit

Travel Planner

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Camino AI travel-planning wrapper, but it sends itinerary and location details to Camino’s API.

Install only if you are comfortable sending travel stops, precise coordinates, stop descriptions, trip constraints, and any trial-signup email to Camino AI. Avoid submitting sensitive home, workplace, medical, legal, or confidential business travel plans unless you trust Camino’s privacy and retention practices, and prefer a limited or trial API key.

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
88% confidence
Finding
The skill documentation instructs users to invoke a local shell script (`./scripts/travel-planner.sh`) and `curl`, which are code-execution capabilities, but the skill metadata only declares an environment variable requirement and no corresponding permissions/capabilities disclosure. This can mislead users and hosts about what the skill actually does, reducing reviewability and increasing the chance that shell-based behavior is executed without appropriate trust or sandbox expectations.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill sends precise latitude/longitude waypoints and user itinerary data to Camino's external API, but the documentation provides no privacy notice, consent guidance, retention statement, or warning that sensitive location/travel patterns are transmitted off-platform. Precise movement and destination data can reveal home/work locations, routines, meetings, or other sensitive personal information if shared unintentionally or logged by third parties.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The script sends the full user-supplied itinerary JSON, including waypoint coordinates and trip details, to an external Camino API without any explicit disclosure, consent prompt, or data-minimization step. In a travel-planning context this can expose sensitive location and behavioral data, and the risk is elevated because exfiltration is the core behavior of the skill rather than an incidental side effect.

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
92% 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/journey" | jq .
Confidence
89% confidence
Finding
https://api.getcamino.ai/

VirusTotal

No VirusTotal findings

View on VirusTotal