ClawHub
Back to skill

Security audit

weather-skill-hangs-001

Security checks for vulnerabilities and agentic risk

Overview

This is a simple mock weather skill with broad but purpose-aligned activation guidance and no evident sensitive access or persistence.

Before installing, understand that this appears to provide simulated weather information, not live forecasts. It is low risk, but users who need accurate current weather should prefer a real weather provider or a skill with clearly disclosed API behavior.

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
90% confidence
Finding
The skill's activation guidance is broad enough to trigger on many generic weather-related requests without clearly defining when this skill should be selected versus handled natively by the host assistant. Over-broad invocation can cause inappropriate routing, unnecessary skill use, or make it easier for a low-value skill to intercept common user requests, though this specific skill appears limited to mock weather responses and does not show direct data-exfiltration or code-execution behavior.

Static analysis

No suspicious patterns detected.