ClawHub
Back to skill

Security audit

Ikuzo - The Map Editor

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Ikuzo travel-planning integration, but it can access and modify saved maps, places, and trips in the connected account.

Install only if you want Codex to work with your Ikuzo account. Be careful with requests involving your current location or saved private places, and specify mapIds or ask before deleting or changing trips when scope matters.

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
95% confidence
Finding

The skill description includes broad triggers like trip planning, location discovery, and "where should I go" questions, which can cause the agent to invoke this skill for ordinary conversation that does not clearly require external tool use. Over-broad activation increases the chance of unnecessary data access or action-taking in a travel account context, especially where maps, spots, and itineraries can be created or modified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The documentation explicitly states that spots_nearby searches across ALL accessible maps, which may aggregate sensitive location-linked data without warning the user. In a location and travel planning skill, this is particularly risky because nearby searches can reveal private saved places, shared-map content, or inferred habits if the tool is invoked without clear disclosure or scope restriction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.