ClawHub
Back to skill

Security audit

Mapbox Maps

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Mapbox development helper with token-safety guidance and no hidden execution, persistence, or data collection behavior.

Before installing, understand that this skill may help generate code that uses a Mapbox access token. Keep tokens scoped, prefer environment or runtime configuration, restrict public tokens by allowed URLs where possible, and avoid pasting real secret tokens into chat.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Credential Access

High
Category
Privilege Escalation
Content
1. Confirm the runtime first: plain HTML, Vite, React, Next.js, or another framework.
2. Confirm which Mapbox surface is involved: GL JS map rendering, styles, tilesets, geocoding, directions, or static images.
3. Start with the smallest working map before adding custom sources, layers, controls, or API calls.
4. Keep access tokens out of source files and examples unless the user explicitly wants a local-only demo.
5. For bugs, isolate whether the failure is in container sizing, token/scopes, style/source IDs, coordinate order, or layer order.

## Implementation Guardrails
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High
Category
Privilege Escalation
Content
- Add sources before layers, and keep layer IDs stable so updates are easy.
- Prefer GeoJSON for lightweight overlays; move to vector tiles or tilesets for larger datasets.
- In React or other SPA frameworks, remove the map instance during teardown to avoid leaks.
- Treat the access token as configuration. Read it from environment or runtime config instead of hardcoding it.

## Common Failure Checks
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Ae1

High
Category
analysis-evasion
Content
- For clawhub.ai publication, keep content reproducible and semver-friendly; put detailed examples in references instead of bloating `SKILL.md`.
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
The description includes a dedicated Chinese-trigger clause ("中文触发：...") as part of the activation guidance, but does not indicate that language selection is optional or that the skill is specifically intended for a Chinese-language context. This can be read as imposing a locale-specific trigger policy without explicit user opt-in or justification.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/patterns.md:44