ClawHub
Back to skill

Security audit

Swiss Geo & Tourism Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a Swiss maps and travel helper with no hidden code, but its outdoor hazard and weather guidance lacks clear safety limits.

Review this skill before installing if you may use it for hiking, skiing, mountain travel, floods, weather, or other safety-sensitive planning. Treat those outputs as informational only, verify timestamps and official real-time bulletins, and do not rely on the skill alone for route safety or emergency decisions.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation description is broad enough to trigger on many general travel, location, attraction, or coordinate questions without clear boundaries such as Switzerland-only scope, non-safety-critical use, or when fresher sources are required. Over-broad activation can cause the agent to invoke this skill in inappropriate contexts and return location, transit, or hazard guidance with unjustified confidence.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill provides avalanche, rockfall, flood, weather, and mountain-related guidance sources but does not prominently warn that these feeds may be incomplete, stale, approximate, or insufficient for real-world safety decisions. In this context, users may rely on the output for outdoor planning, creating a meaningful risk of physical harm if conditions have changed or the queried layers are not authoritative for go/no-go decisions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.