ClawHub
Back to skill

Security audit

Mapbox Style Patterns

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Mapbox styling recipe library; it does not install code or access data, though location-tracking examples need privacy-aware use.

Installers should treat this as a style-reference skill. When using the delivery or navigation patterns, add your own privacy safeguards for location data, including clear consent, limited precision/update frequency, restricted visibility, and short retention.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Whitespace Padding

Medium
Category
Prompt Injection
Content
Additional patterns and configurations are available in the `references/` directory. Load the relevant file when a specific pattern is needed.

| File                                                                         | Contents                                                                                         |
| ---------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ |
| [references/real-estate.md](references/real-estate.md)                       | Pattern 2: Real Estate Map -- property boundaries, price color-coding, amenity markers           |
| [references/data-viz-base.md](references/data-viz-base.md)                   | Pattern 3: Data Visualization Base Map -- minimal grayscale base for choropleth/heatmap overlays |
Confidence
70% confidence
Finding
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The 'Invoke this skill when' list uses broad conditions such as 'starting a new map style,' 'optimizing existing styles,' and 'debugging style issues' without clarifying when this skill should be preferred over other Mapbox or debugging skills. That ambiguity can cause unintended or overly frequent invocation because the trigger scope is not narrowly constrained.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly promotes real-time tracking of drivers and customers and provides implementation patterns for displaying live locations, ETA, bearing, and route progress without any accompanying privacy, consent, retention, or minimization guidance. In a delivery/logistics context this can normalize collection and exposure of sensitive location data, increasing risk of stalking, worker surveillance misuse, or accidental disclosure if adopted as-is.

Static analysis

No suspicious patterns detected.