ClawHub
Back to skill

Security audit

Mapbox Cartography

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Mapbox cartography guidance skill with no executable behavior, persistence, credential use, or hidden high-impact actions.

Safe to install for Mapbox and cartography assistance. Be aware it may be invoked for general map-design discussions because its trigger language is broad, but the inspected content is advisory and does not perform actions on your system or accounts.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The 'Invoke this skill when' list consists of general activities like choosing colors, making visual hierarchy decisions, and troubleshooting visibility issues, which can occur in many ordinary mapping conversations. The file does not provide tighter scope, explicit trigger phrases, or negative examples clarifying when the skill should not activate.

Static analysis

No suspicious patterns detected.