ClawHub
Back to skill

Security audit

Aviation Weather

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches aviation weather from a disclosed government weather API and does not show hidden, persistent, or destructive behavior.

Before installing, understand that using the skill will make live requests to aviationweather.gov with airport codes or latitude/longitude values you provide. It appears narrowly scoped to weather lookup, but a stricter manifest declaring that network scope would improve auditability.

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 (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill instructs use of a network-capable script to fetch live data from aviationweather.gov, but the manifest declares no explicit tool scope such as permissions or allowed-tools. That creates an authorization and governance gap: an agent may be able to make outbound requests without the skill clearly declaring that capability, reducing auditability and increasing the chance of unintended or policy-violating network access.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.