ClawHub
Back to skill

Security audit

Thailand

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Thailand travel and relocation guide with scoped local memory, and I found no deceptive, destructive, or exfiltration behavior.

Before installing, understand that the skill may keep a local ~/thailand/memory.md file with travel or relocation preferences and constraints. That can be useful for personalization, but review or delete it if it contains sensitive visa, health, family, work, or budget details you do not want persisted.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Natural-Language Policy Violations

Medium
Confidence
78% confidence
Finding
The title explicitly constrains the skill content to Thailand, which is a locale-specific restriction. In this file, that regional limitation is not presented as an optional user choice or justified as a clearly region-specific compliance/travel tool, so it can violate the policy against forcing a locale without opt-in.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly creates and updates a local memory file to store user context, but it does not clearly disclose to the user that conversation details may be persisted on disk and later reused. This creates a privacy risk because travel, relocation, visa, health, family, and work-related constraints can be sensitive, and users may reasonably assume the conversation is ephemeral unless told otherwise.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Content
```bash
mkdir -p ~/thailand
touch ~/thailand/memory.md
chmod 700 ~/thailand
chmod 600 ~/thailand/memory.md
```
Confidence
80% confidence
Finding
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Content
mkdir -p ~/thailand
touch ~/thailand/memory.md
chmod 700 ~/thailand
chmod 600 ~/thailand/memory.md
```

If `~/thailand/memory.md` is empty, initialize it from `memory-template.md`.
Confidence
80% confidence
Finding
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Natural-Language Policy Violations

Medium
Confidence
98% confidence
Finding
The instruction to read stored memory silently means prior user data is reused without fresh visibility or awareness at the time of access. This weakens informed consent and can surprise users, especially when the stored data may include sensitive personal preferences or constraints related to relocation, health, family, visa status, or finances.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Core Principle

Visa planning should be treated as a dynamic system. Do not finalize flights, schools, or long leases without checking official portals for the user nationality and travel date.

## Major Pathways (check latest rules)
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Natural-Language Policy Violations

Low
Confidence
83% confidence
Finding
The file presents all user-facing guidance in English and does not indicate that users may choose another language or that English is required for a justified regional or compliance reason. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.