ClawHub
Back to skill

Security audit

Urban Daoist Navigator

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only daily-planning style skill with no executable code, persistence, credential handling, or hidden data movement.

Install only if you want routine planning advice framed through Eastern philosophy. Be aware that it may activate for general daily-planning prompts and may answer in English even in multilingual contexts; keep any calendar, location, or weather access under your direct control.

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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger description is broad enough to match many ordinary requests such as daily planning, morning routine, or general mood-setting, which increases the chance this skill activates when the user did not specifically ask for it. In an agent system, overbroad activation can override more appropriate skills, inject unsolicited behavioral framing, and expand the skill's influence beyond its intended niche.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
Forcing English output without checking the user's preferred language can cause the agent to ignore user context and reduce usability, especially in multilingual conversations. While not a classic security flaw, it is a policy and alignment weakness because the skill may override higher-priority language expectations and produce inappropriate responses for the user.

Static analysis

No suspicious patterns detected.