ClawHub
Back to skill

Security audit

Ecommerce Copy Humanizer TH

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow Thai ecommerce copy rewriting skill with no code execution, network access, credential use, or persistence.

Install this only if you want help rewriting Thai ecommerce copy. It is not intended for translation, bilingual localization, or regulated compliance review.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file states the skill is 'Thai only,' requires input primarily in Thai, and requires output to stay in Thai. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly justified as region-specific or the user is given a choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.