ClawHub
Back to skill

Security audit

Norway Roads

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused Norway road-conditions helper that only queries a disclosed public road-data API and does not show hidden persistence, credential use, or destructive behavior.

Install this only if you are comfortable with the skill making live HTTPS requests to Statens Vegvesen's NVDB API for Norway road data. It does not need API keys and I found no evidence of local credential access, persistence, or destructive actions.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documentation instructs execution of a network-capable script against an external API, but the skill manifest declares no explicit tool scope such as allowed network access. This creates a least-privilege and governance gap: an agent or reviewer cannot reliably tell what external capabilities the skill is intended to use, increasing the risk of unintended data egress or misuse if the skill is invoked in broader contexts.

Natural-Language Policy Violations

Low
Confidence
77% confidence
Finding
The reference section centers Norwegian labels such as 'Vegidentitet', 'Beskrivelse', and 'Alvorlighetsgrad' alongside English glosses, but the document does not state whether users can choose a preferred language or locale. Because SQP-3 covers language/locale policy concerns, this can be read as imposing a locale-specific presentation by default.

Static analysis

No suspicious patterns detected.