ClawHub
Back to skill

Security audit

Model Prompt Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill only turns user-provided clothing descriptions into short English image-generation prompts and does not request system access, credentials, persistence, or external execution.

Installers should understand that this skill is narrowly designed to return only a short English prompt, so it may not provide explanations or Chinese-language output even when the user asks. There is no evidence of hidden code execution, data access, persistence, or exfiltration in the inspected artifact.

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
95% confidence
Finding

The skill requires that the output be 'only one English prompt' and further prohibits Chinese explanations or additional notes. This imposes a specific language policy regardless of user preference, and the file does not offer any language choice or opt-in mechanism.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.